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

    Neuronpedia

    INDEX
    Explanations

    references to expertise and the need for assistance

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

    knowing what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Microkernel
    -0.60
    AnchorStyles
    -0.60
    CodeAttribute
    -0.55
    WebVitals
    -0.54
     GenerationType
    -0.52
    Tembelea
    -0.52
     betweenstory
    -0.50
    styleType
    -0.49
    ItemBackground
    -0.47
    Personensuche
    -0.46
    POSITIVE LOGITS
    +#+#
    0.42
     مرئيه
    0.41
    Ārējās
    0.34
    middag
    0.32
    cektir
    0.31
     Whi
    0.31
    dicht
    0.31
     aí
    0.30
     Say
    0.30
    pragma
    0.30
    Act Density 0.015%

    No Known Activations