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

    Neuronpedia

    INDEX
    Explanations

    arithmetic calculations and mathematical equations

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    erif
    -0.07
    ilar
    -0.07
    amarin
    -0.07
    OrElse
    -0.07
    åde
    -0.07
    à¥Ŀ
    -0.06
    mür
    -0.06
    okable
    -0.06
     salopes
    -0.06
    getDisplay
    -0.06
    POSITIVE LOGITS
     negative
    0.13
     Negative
    0.11
    Negative
    0.10
    (-
    0.10
    è´Ł
    0.10
     (-
    0.10
     anti
    0.09
    negative
    0.09
    -negative
    0.09
     minus
    0.09
    Act Density 0.650%

    No Known Activations