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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and expressions of expectation or prediction

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

    Following "of" or "the"

    np_acts-logits-general · gemini-2.0-flash

    aforementioned or similar phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     विश्वसनीयता
    -0.64
    elsif
    -0.62
    τογραφ
    -0.59
    BeginContext
    -0.57
    AndEndTag
    -0.57
    RenderAtEndOf
    -0.55
     Signalez
    -0.54
    ViewImports
    -0.53
    OPHY
    -0.52
    ArrowToggle
    -0.52
    POSITIVE LOGITS
     sådan
    0.69
    此事
    0.67
     ilyen
    0.66
     solche
    0.63
     problemet
    0.63
     подоб
    0.62
     aforesaid
    0.62
    这个问题
    0.62
    这件事
    0.61
     dimaksud
    0.60
    Act Density 0.624%

    No Known Activations