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

    Neuronpedia

    INDEX
    Explanations

    block

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ourses
    -0.07
    (ct
    -0.07
    444
    -0.07
    рок
    -0.06
    _RF
    -0.06
     lighting
    -0.06
     seemingly
    -0.06
    ame
    -0.06
    اث
    -0.06
     RA
    -0.06
    POSITIVE LOGITS
     Libyan
    0.06
    )animated
    0.06
     ness
    0.06
    裏
    0.06
     لذا
    0.06
    .Down
    0.06
    _production
    0.06
    σιμοποι
    0.06
    nature
    0.06
     bmp
    0.06
    Act Density 0.007%

    No Known Activations