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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gegen
    -0.07
    ̃
    -0.06
    .googleapis
    -0.06
    (hidden
    -0.06
    说话
    -0.06
     Candle
    -0.06
    (description
    -0.06
     exploded
    -0.06
    ियत
    -0.06
    136
    -0.06
    POSITIVE LOGITS
     '';↵↵
    0.07
    .production
    0.07
    eresa
    0.07
    سة
    0.06
     Sey
    0.06
    競
    0.06
    мотр
    0.06
     hires
    0.06
     Similarly
    0.06
     GAME
    0.06
    Act Density 0.003%

    No Known Activations