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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dr
    -0.07
    irectory
    -0.07
    节
    -0.06
    Road
    -0.06
    \Factory
    -0.06
     Falling
    -0.06
    IllegalArgumentException
    -0.06
    Gener
    -0.06
    --------------------------------------------------------------------------------
    -0.06
     Time
    -0.06
    POSITIVE LOGITS
     slav
    0.06
    .XtraEditors
    0.06
    ocoa
    0.06
    ]+$
    0.06
    لي
    0.06
    _Click
    0.06
     airflow
    0.06
    لم
    0.06
    /about
    0.06
    uset
    0.05
    Act Density 0.004%

    No Known Activations