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

    Neuronpedia

    INDEX
    Explanations

    Defendant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _gener
    -0.07
    .comboBox
    -0.07
    婦
    -0.07
    ('[
    -0.06
    Bien
    -0.06
     trabaj
    -0.06
    entries
    -0.06
     çevr
    -0.06
     SCN
    -0.06
    _x
    -0.06
    POSITIVE LOGITS
    决定
    0.07
    .Reverse
    0.06
     improves
    0.06
    aversable
    0.06
    ellaneous
    0.06
    iterate
    0.06
    ンデ
    0.06
     Operator
    0.06
    Validator
    0.06
    隆
    0.06
    Act Density 0.005%

    No Known Activations