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

    Neuronpedia

    INDEX
    Explanations

    tal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    4
    -0.07
    abies
    -0.07
     cut
    -0.07
     punish
    -0.07
    ucene
    -0.07
    店里
    -0.07
    .ed
    -0.07
     pond
    -0.07
    똥
    -0.06
    'id
    -0.06
    POSITIVE LOGITS
     acest
    0.07
     cả
    0.07
    zá
    0.07
    最も
    0.07
     saat
    0.07
    *>(&
    0.06
     Teil
    0.06
    ază
    0.06
    _days
    0.06
    \",\
    0.06
    Act Density 0.079%

    No Known Activations