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

    Neuronpedia

    INDEX
    Explanations

    individual influence/action

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    exp
    -0.07
    _sigma
    -0.07
    _PIPE
    -0.07
    .btnDelete
    -0.06
    mine
    -0.06
    _Tree
    -0.06
     BPM
    -0.06
    _cell
    -0.06
     Guil
    -0.06
    ozem
    -0.06
    POSITIVE LOGITS
     |\
    0.06
     nombres
    0.06
    ;padding
    0.06
     ]↵↵
    0.06
     ณ
    0.06
    .getLabel
    0.06
     sebep
    0.06
    보다
    0.06
     hå
    0.06
    ган
    0.06
    Act Density 0.070%

    No Known Activations