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

    Neuronpedia

    INDEX
    Explanations

    Comparisons and generalizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     morals
    -0.07
     booking
    -0.07
     compute
    -0.07
     Cars
    -0.07
    ewed
    -0.06
     Yuan
    -0.06
    Worker
    -0.06
     choices
    -0.06
    li
    -0.06
    ?>>
    -0.06
    POSITIVE LOGITS
     хви
    0.07
     İmpar
    0.06
     Пар
    0.06
    -meta
    0.06
    ิร
    0.06
    _MISS
    0.06
    JNIEXPORT
    0.06
     팬
    0.06
     kişisel
    0.06
    フェ
    0.06
    Act Density 0.185%

    No Known Activations