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

    Neuronpedia

    INDEX
    Explanations

    correct

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .slides
    -0.07
    FileDialog
    -0.07
    שדה
    -0.07
     ally
    -0.07
    Ѷ
    -0.07
    ♗
    -0.07
    _fail
    -0.07
    Angle
    -0.06
     المحلية
    -0.06
    '''
↵
    -0.06
    POSITIVE LOGITS
    bern
    0.08
     Kemp
    0.07
    创立
    0.07
     Sz
    0.07
    -str
    0.07
    łatw
    0.07
    ᡠ
    0.06
    cj
    0.06
    점을
    0.06
    工程施工
    0.06
    Act Density 0.071%

    No Known Activations