Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    sentences that describe the characteristics or functionalities of structures or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "is" followed by location/state description

    np_acts-logits-general · gemini-2.0-flash

    describing composition or location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EndContext
    -0.82
    IntoConstraints
    -0.81
     виправивши
    -0.81
    -0.73
    تقاوى
    -0.68
     ModelExpression
    -0.67
    سطس
    -0.67
    RectangleBorder
    -0.66
     مشين
    -0.64
    +#+#
    -0.63
    POSITIVE LOGITS
     divided
    0.72
     powered
    0.69
     based
    0.68
     characterized
    0.65
     composed
    0.64
     accompanied
    0.63
     comprised
    0.63
     part
    0.62
    divided
    0.62
     supported
    0.61
    Act Density 0.386%

    No Known Activations