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

    Neuronpedia

    INDEX
    Explanations

    Scientific measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -btn
    -0.07
    ються
    -0.07
    еть
    -0.06
     runoff
    -0.06
     '''↵↵
    -0.06
    -designed
    -0.06
     """
↵
    -0.06
     захисту
    -0.06
    Spanish
    -0.06
    Lost
    -0.06
    POSITIVE LOGITS
     Scre
    0.07
     Cement
    0.07
    >v
    0.07
    elerden
    0.07
    니아
    0.07
    .getTime
    0.06
     Typed
    0.06
    äge
    0.06
     Thick
    0.06
     tín
    0.06
    Act Density 0.049%

    No Known Activations