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

    Neuronpedia

    INDEX
    Explanations

    treatment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mode
    -0.07
     Cou
    -0.06
    信息
    -0.06
     Manuel
    -0.06
    シャル
    -0.06
     칼
    -0.06
    熊
    -0.06
    Fu
    -0.06
     Godzilla
    -0.06
     skipped
    -0.06
    POSITIVE LOGITS
     remover
    0.07
    .Undef
    0.06
    (init
    0.06
    (move
    0.06
    :Object
    0.06
    toggle
    0.06
     Whisper
    0.06
    .health
    0.06
     Steele
    0.06
    .libs
    0.06
    Act Density 0.030%

    No Known Activations