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

    Neuronpedia

    INDEX
    Explanations

    ac

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sessionId
    -0.07
    privileged
    -0.06
    .putString
    -0.06
     responsable
    -0.06
    _cid
    -0.06
     Pre
    -0.06
     PA
    -0.06
     combinations
    -0.06
     nip
    -0.06
     Restr
    -0.06
    POSITIVE LOGITS
    CLUDING
    0.06
    car
    0.06
    상
    0.06
    lac
    0.06
     більше
    0.06
    नल
    0.06
    Accessory
    0.06
     Toolkit
    0.06
    接着
    0.06
    ateř
    0.06
    Act Density 0.003%

    No Known Activations