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

    Neuronpedia

    INDEX
    Explanations

    Dress descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fr
    -0.07
    .relative
    -0.07
     sand
    -0.07
    .fragments
    -0.07
    imeters
    -0.06
    _Detail
    -0.06
    classifier
    -0.06
    ễ
    -0.06
     wizards
    -0.06
    asm
    -0.06
    POSITIVE LOGITS
     utf
    0.07
    有色
    0.07
     Utf
    0.06
     foreseeable
    0.06
    ethyl
    0.06
    حلة
    0.06
    ała
    0.06
     Wells
    0.06
     neo
    0.06
    柯
    0.06
    Act Density 0.044%

    No Known Activations