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

    Neuronpedia

    INDEX
    Explanations

    math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mis
    -0.07
    숙
    -0.06
    kok
    -0.06
     detections
    -0.06
    561
    -0.06
     他
    -0.06
     remedies
    -0.06
     pill
    -0.06
     nostra
    -0.06
    -->↵↵
    -0.06
    POSITIVE LOGITS
    .titleLabel
    0.08
     OnClickListener
    0.07
     lineNumber
    0.06
    .HashSet
    0.06
    Dirty
    0.06
     Shuttle
    0.06
     Dirty
    0.06
    .EventArgs
    0.06
    .setOn
    0.06
     garbage
    0.06
    Act Density 0.016%

    No Known Activations