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

    Neuronpedia

    INDEX
    Explanations

    pearance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MatTable
    -0.09
     gameTime
    -0.07
    ﰠ
    -0.07
    /Grid
    -0.07
    持仓
    -0.07
    �
    -0.07
    rng
    -0.07
     franchises
    -0.07
    睃
    -0.07
     note
    -0.06
    POSITIVE LOGITS
    _devices
    0.07
     bury
    0.07
     cover
    0.07
    _assoc
    0.06
    _least
    0.06
    的人来说
    0.06
    LK
    0.06
    Policy
    0.06
     Structure
    0.06
    更高
    0.06
    Act Density 0.000%

    No Known Activations