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

    Neuronpedia

    INDEX
    Explanations

    knee

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sabe
    -0.07
     tres
    -0.07
    rám
    -0.06
     lety
    -0.06
     الخارج
    -0.06
     rte
    -0.06
     ﾄ
    -0.06
     welcoming
    -0.06
    _TRAN
    -0.06
    .neg
    -0.06
    POSITIVE LOGITS
     battlefield
    0.07
     Westminster
    0.07
     battleground
    0.07
    conversion
    0.07
     плеч
    0.07
     running
    0.07
    _pointer
    0.06
     inactive
    0.06
    ンバー
    0.06
    Distinct
    0.06
    Act Density 0.008%

    No Known Activations