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

    Neuronpedia

    INDEX
    Explanations

    For

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .tex
    -0.06
    *>&
    -0.06
     Sc
    -0.06
     Gates
    -0.06
    .Progress
    -0.06
    Ш
    -0.06
    	CC
    -0.06
    ゲーム
    -0.06
    _pool
    -0.06
    Apr
    -0.06
    POSITIVE LOGITS
     움
    0.07
    .lon
    0.07
    üns
    0.07
    िद
    0.06
    เภ
    0.06
    _tuple
    0.06
     personn
    0.06
    itzer
    0.06
     refreshToken
    0.06
    （笑
    0.06
    Act Density 0.011%

    No Known Activations