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

    Neuronpedia

    INDEX
    Explanations

    code documentation and assembly settings

    oai_token-act-pair · gemini-2.0-flash

    //

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uxxxx
    -0.85
    IVEREF
    -0.83
     ComVisible
    -0.82
    DeleteBehavior
    -0.82
    WebVitals
    -0.82
     Мексичка
    -0.82
    RenderAtEndOf
    -0.81
    thâu
    -0.79
    хьтан
    -0.79
    Климат
    -0.77
    POSITIVE LOGITS
    ↵
    0.45
    </td>
    0.45
    </h3>
    0.43
     
    0.42
     den
    0.41
     Third
    0.41
    ↵↵
    0.40
    </sub>
    0.39
     ***!
    0.38
    </strong>
    0.37
    Act Density 0.232%

    No Known Activations