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

    Neuronpedia

    INDEX
    Explanations

    rare

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     normalized
    -0.07
    ımızı
    -0.07
     bigger
    -0.06
    ไฟล
    -0.06
    _n
    -0.06
     tidy
    -0.06
     PSU
    -0.06
     öğretmen
    -0.06
    normalized
    -0.06
     пацієн
    -0.06
    POSITIVE LOGITS
     rare
    0.12
     Rare
    0.11
    Rare
    0.09
    تن
    0.07
     sor
    0.06
    illing
    0.06
    .short
    0.06
    .sp
    0.06
    ορ
    0.06
    det
    0.06
    Act Density 0.012%

    No Known Activations