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

    Neuronpedia

    INDEX
    Explanations

    suggestions and support

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aved
    -0.07
    Ana
    -0.07
    ुड
    -0.07
     swe
    -0.06
    557
    -0.06
    bbie
    -0.06
    :flutter
    -0.06
     cooperate
    -0.06
    included
    -0.06
    찰
    -0.06
    POSITIVE LOGITS
    _FLOAT
    0.07
     ::
    0.07
     rm
    0.06
    ;:;:;:;:
    0.06
     bewild
    0.06
     naam
    0.06
    세요
    0.06
    .↵↵↵↵↵↵↵↵
    0.06
    )、
    0.06
     coined
    0.06
    Act Density 0.084%

    No Known Activations