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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     beside
    -0.07
     suffice
    -0.07
    atum
    -0.07
    ?"
    -0.07
     khớp
    -0.07
    ℬ
    -0.07
     Paste
    -0.06
    责任
    -0.06
    唬
    -0.06
     moden
    -0.06
    POSITIVE LOGITS
    _multiplier
    0.07
    뇐
    0.07
     intervening
    0.07
    rength
    0.07
     alumni
    0.06
    廣
    0.06
    �
    0.06
    cluster
    0.06
     achievements
    0.06
    ijkstra
    0.06
    Act Density 0.000%

    No Known Activations