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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (I
    -0.07
     při
    -0.06
    Glyph
    -0.06
     GMC
    -0.06
    ologie
    -0.06
    OUNCE
    -0.06
    Teacher
    -0.06
    ь
    -0.06
    (""+
    -0.06
    (userName
    -0.06
    POSITIVE LOGITS
     ніч
    0.07
    .connect
    0.07
     Chattanooga
    0.07
    __':
↵
    0.07
    缘
    0.06
     exhilar
    0.06
    _IOCTL
    0.06
     któ
    0.06
     FRIEND
    0.06
    合わせ
    0.06
    Act Density 0.004%

    No Known Activations