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

    Neuronpedia

    INDEX
    Explanations

    Parentheses and dashes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fiction
    -0.07
     ẩn
    -0.07
    яем
    -0.06
    ovie
    -0.06
    vertis
    -0.06
     Politics
    -0.06
    ㅋ
    -0.06
     FPS
    -0.06
    -await
    -0.06
     fingers
    -0.06
    POSITIVE LOGITS
    .`);↵
    0.08
     combust
    0.07
    ()})↵
    0.07
    _sun
    0.06
    еристи
    0.06
     idol
    0.06
    #import
    0.06
     sloppy
    0.06
     перв
    0.06
    --;
↵
    0.06
    Act Density 0.000%

    No Known Activations