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

    Neuronpedia

    INDEX
    Explanations

    j

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Christian
    -0.07
     rua
    -0.07
    ер
    -0.07
     Punjab
    -0.07
    ière
    -0.07
    Ins
    -0.06
    oram
    -0.06
    땄
    -0.06
    uler
    -0.06
    .magic
    -0.06
    POSITIVE LOGITS
     Moodle
    0.08
    เคร
    0.08
     (#
    0.07
     ملف
    0.07
    迫不及
    0.07
     weary
    0.07
    멧
    0.07
    粽子
    0.07
    ensely
    0.07
    .initialize
    0.07
    Act Density 0.002%

    No Known Activations