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

    Neuronpedia

    INDEX
    Explanations

    word

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     equivalent
    -0.06
    dbe
    -0.06
    截
    -0.06
     analysed
    -0.06
    _cr
    -0.06
     говорит
    -0.06
    стра
    -0.06
    уж
    -0.05
    скому
    -0.05
    678
    -0.05
    POSITIVE LOGITS
     superheroes
    0.07
    KNOWN
    0.07
    ど
    0.06
     Grape
    0.06
    ]];↵
    0.06
    ظ
    0.06
    INARY
    0.06
     LEGO
    0.06
     Hawkins
    0.06
     teşekkür
    0.06
    Act Density 0.003%

    No Known Activations