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

    Neuronpedia

    INDEX
    Explanations

    swiping or personalization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nakalista
    -0.98
     defaultstate
    -0.91
     Савезне
    -0.90
    Personensuche
    -0.90
     متعلقه
    -0.88
     autorytatywna
    -0.88
    AndEndTag
    -0.86
    Portale
    -0.82
    PYX
    -0.80
    出版年
    -0.79
    POSITIVE LOGITS
    orkin
    0.47
     with
    0.45
    a
    0.43
     altri
    0.40
    clearInterval
    0.39
    es
    0.39
    ه
    0.39
    い
    0.38
     Step
    0.38
     another
    0.38
    Act Density 0.022%

    No Known Activations