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

    Neuronpedia

    INDEX
    Explanations

    non-english text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     coil
    -0.07
     FIXME
    -0.07
     наг
    -0.06
     bek
    -0.06
     Are
    -0.06
     نس
    -0.06
     ecstasy
    -0.06
    ンダ
    -0.06
    .layout
    -0.06
     thunder
    -0.06
    POSITIVE LOGITS
    IGNORE
    0.07
    metro
    0.06
     Wu
    0.06
    ,address
    0.06
    'nın
    0.06
    /lgpl
    0.06
    \u
    0.06
    :m
    0.06
    /register
    0.06
     خلال
    0.06
    Act Density 0.113%

    No Known Activations