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

    Neuronpedia

    INDEX
    Explanations

    using

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cult
    -0.08
    ปาก
    -0.08
    プリン
    -0.07
    מחיר
    -0.07
    isex
    -0.07
    批发
    -0.07
     Intellectual
    -0.07
    捐助
    -0.07
     мяс
    -0.07
    _tm
    -0.07
    POSITIVE LOGITS
     dismant
    0.08
     про
    0.07
    跸
    0.07
    _ADAPTER
    0.07
     Terra
    0.07
    尸
    0.07
     שת
    0.07
     measurements
    0.07
     &#
    0.07
     extraordin
    0.07
    Act Density 0.977%

    No Known Activations