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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _LINES
    -0.07
    /tools
    -0.06
    獲得
    -0.06
    Replace
    -0.06
    -ending
    -0.06
    _STATES
    -0.06
    -gr
    -0.06
    ParameterValue
    -0.06
    Users
    -0.06
    .policy
    -0.06
    POSITIVE LOGITS
    殖
    0.06
     redundancy
    0.06
    oplast
    0.06
    ẫ
    0.06
     waking
    0.06
    ности
    0.06
    =q
    0.06
    351
    0.06
    _NPC
    0.06
     Ubisoft
    0.06
    Act Density 0.142%

    No Known Activations