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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    figcaption
    -0.08
     пог
    -0.07
    _frac
    -0.06
     Prozent
    -0.06
    égor
    -0.06
    _grp
    -0.06
    	TokenName
    -0.06
    ::::|
    -0.06
    ительства
    -0.06
    olute
    -0.06
    POSITIVE LOGITS
     appeared
    0.06
     всей
    0.06
     言
    0.06
    Ì
    0.06
    대회
    0.06
    \Abstract
    0.06
    Greetings
    0.06
    arming
    0.06
     відбу
    0.06
    juries
    0.06
    Act Density 0.019%

    No Known Activations