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

    Neuronpedia

    INDEX
    Explanations

    Abstinence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kır
    -0.07
     casos
    -0.07
     jeopardy
    -0.07
    .Series
    -0.07
    (scanner
    -0.06
     Surely
    -0.06
    asics
    -0.06
    _tags
    -0.06
     pioneering
    -0.06
     فلس
    -0.06
    POSITIVE LOGITS
     abst
    0.11
    stinence
    0.09
     skeletons
    0.07
    sters
    0.07
     straight
    0.07
    isters
    0.07
    Straight
    0.06
    澳
    0.06
     बच
    0.06
    istrates
    0.06
    Act Density 0.002%

    No Known Activations