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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prejudices
    -0.06
    attachments
    -0.06
     hòa
    -0.06
     grave
    -0.06
    โจ
    -0.06
    tog
    -0.06
     outspoken
    -0.06
    �y
    -0.06
     hin
    -0.06
     Fahrenheit
    -0.06
    POSITIVE LOGITS
    ész
    0.07
    ье
    0.06
     Miche
    0.06
     getField
    0.06
    _MAKE
    0.06
     станов
    0.06
     şar
    0.06
    ！
    0.06
     minh
    0.06
     differentiated
    0.06
    Act Density 0.066%

    No Known Activations