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

    Neuronpedia

    INDEX
    Explanations

    chair

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    '";
↵
    -0.07
     Clint
    -0.07
    .getBoolean
    -0.07
    (Transaction
    -0.07
     איתו
    -0.07
     Daddy
    -0.07
     המחיר
    -0.07
     helping
    -0.07
     addition
    -0.07
    陆
    -0.07
    POSITIVE LOGITS
     fab
    0.08
     Repo
    0.08
    淟
    0.07
    调控
    0.07
    嬖
    0.07
    Fail
    0.07
    玖
    0.07
     escol
    0.07
    ire
    0.07
    oir
    0.07
    Act Density 0.002%

    No Known Activations