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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    говор
    -0.06
    ्श
    -0.06
     �
    -0.06
     đẳng
    -0.06
     přib
    -0.06
     भ
    -0.06
    /ip
    -0.06
    iloc
    -0.06
     یه
    -0.06
    _rgba
    -0.06
    POSITIVE LOGITS
    _take
    0.07
     publicity
    0.07
     Conspiracy
    0.07
     Strategies
    0.07
    Skipping
    0.07
    (signature
    0.06
     agreement
    0.06
     logic
    0.06
     Debate
    0.06
     salute
    0.06
    Act Density 0.590%

    No Known Activations