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

    Neuronpedia

    INDEX
    Explanations

    semicolon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     credential
    -0.07
     berries
    -0.06
     他
    -0.06
     )->
    -0.06
    Question
    -0.06
     smashed
    -0.06
    illo
    -0.06
    got
    -0.06
     servi
    -0.06
     kia
    -0.06
    POSITIVE LOGITS
    __(*
    0.07
    alien
    0.07
    ickém
    0.06
    (en
    0.06
    غال
    0.06
    _unlock
    0.06
    ibus
    0.06
    ‌هاي
    0.06
     modulo
    0.06
    (handles
    0.06
    Act Density 0.018%

    No Known Activations