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

    Neuronpedia

    INDEX
    Explanations

    say animal food

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fair
    -0.07
     Fair
    -0.06
     Stout
    -0.06
     Door
    -0.06
    Trail
    -0.06
    archivo
    -0.06
    .setup
    -0.06
    Orth
    -0.06
    _mm
    -0.06
    ponential
    -0.06
    POSITIVE LOGITS
     ***/↵
    0.07
     ComponentFixture
    0.07
     adlı
    0.06
    �
    0.06
     haf
    0.06
     робіт
    0.06
     Matters
    0.06
    ैं
    0.06
    bitset
    0.06
    Breaking
    0.06
    Act Density 0.018%

    No Known Activations