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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     =>$
    -0.08
    莿
    -0.07
    妊
    -0.07
    _Construct
    -0.07
    إعل
    -0.07
    ?q
    -0.07
    壬
    -0.06
     עומ
    -0.06
     demonstr
    -0.06
    ರ
    -0.06
    POSITIVE LOGITS
     Mobility
    0.08
    修建
    0.07
    .WriteHeader
    0.07
    iation
    0.07
    _help
    0.07
     Drew
    0.07
    集成
    0.07
     Wal
    0.07
    .getValue
    0.07
    arrière
    0.07
    Act Density 0.090%

    No Known Activations