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

    Neuronpedia

    INDEX
    Explanations

    bullet points and items in a list format

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

    bullet points followed by words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Finally
    -0.40
    ↵↵↵
    -0.36
     Even
    -0.35
     finally
    -0.35
    Finally
    -0.34
     Winaray
    -0.34
    asteroide
    -0.33
    .
    -0.32
    ↵↵
    -0.31
    Finalmente
    -0.31
    POSITIVE LOGITS
     ujednoznacz
    0.68
    rungsseite
    0.66
    FunctionFlags
    0.63
    AndEndTag
    0.63
    RenderAtEndOf
    0.60
     useAppContext
    0.60
    vignon
    0.60
    bibnamefont
    0.59
     nakalista
    0.57
    ፩
    0.57
    Act Density 0.025%

    No Known Activations