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

    Neuronpedia

    INDEX
    Explanations

    !

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     giriş
    -0.07
     NETWORK
    -0.06
     คาส
    -0.06
     втра
    -0.06
     призна
    -0.06
     Giang
    -0.06
    LOCITY
    -0.06
    Bed
    -0.06
    هایی
    -0.06
     gran
    -0.06
    POSITIVE LOGITS
     Sixth
    0.07
    بت
    0.07
     initialize
    0.07
    __
↵
    0.07
     fatalError
    0.07
    :before
    0.07
     کنند
    0.07
    asl
    0.06
    -т
    0.06
    committee
    0.06
    Act Density 0.001%

    No Known Activations