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

    Neuronpedia

    INDEX
    Explanations

    Specifications/rules

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    opy
    -0.07
    ество
    -0.07
    (hero
    -0.07
     Nurse
    -0.07
     topics
    -0.07
    ᐊ
    -0.06
    ผลกระทบ
    -0.06
    accountId
    -0.06
     подроб
    -0.06
    危害
    -0.06
    POSITIVE LOGITS
    呗
    0.07
    _BIN
    0.07
     CPL
    0.07
    ATING
    0.06
     Allocator
    0.06
    靜
    0.06
    .Mult
    0.06
    .comboBox
    0.06
     далек
    0.06
    asl
    0.06
    Act Density 0.077%

    No Known Activations