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

    Neuronpedia

    INDEX
    Explanations

    code and filenames

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .).↵↵
    -0.07
    _enum
    -0.06
     '/'↵
    -0.06
    ünde
    -0.06
    ै?
    -0.06
    \Annotation
    -0.06
    such
    -0.06
    ).↵↵
    -0.06
     aging
    -0.06
    modern
    -0.06
    POSITIVE LOGITS
    unched
    0.07
    .WRAP
    0.07
     تقویت
    0.06
    ﾄ
    0.06
     budete
    0.06
     uten
    0.06
     XF
    0.06
     şeklinde
    0.06
    -ab
    0.06
    antal
    0.06
    Act Density 0.049%

    No Known Activations