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

    Neuronpedia

    INDEX
    Explanations

    Trash containers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     OPER
    -0.08
    وذ
    -0.07
    izm
    -0.07
     अवध
    -0.07
     ECC
    -0.06
    技術
    -0.06
    _RSA
    -0.06
    FA
    -0.06
     introduction
    -0.06
     cosplay
    -0.06
    POSITIVE LOGITS
    _InternalArray
    0.07
     directory
    0.07
     enacted
    0.06
    mann
    0.06
    lux
    0.06
    金额
    0.06
     subpoena
    0.06
    584
    0.06
     deton
    0.06
     Creative
    0.06
    Act Density 0.008%

    No Known Activations