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

    Neuronpedia

    INDEX
    Explanations

    logical conditions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     завд
    -0.06
     cộng
    -0.06
     Crime
    -0.06
     Βασ
    -0.06
    _domains
    -0.06
    _FETCH
    -0.06
     Herb
    -0.06
     بنا
    -0.06
    Tail
    -0.06
    モデル
    -0.06
    POSITIVE LOGITS
     untreated
    0.07
     substitution
    0.07
    えて
    0.07
    _utf
    0.07
     справ
    0.07
    _nd
    0.06
    vit
    0.06
     inability
    0.06
    phia
    0.06
    μος
    0.06
    Act Density 0.033%

    No Known Activations