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

    Neuronpedia

    INDEX
    Explanations

    Russian greetings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Pr
    -0.07
     Summon
    -0.07
     commodo
    -0.06
     Dillon
    -0.06
    存量
    -0.06
    -motion
    -0.06
    iciel
    -0.06
    资产评估
    -0.06
     attic
    -0.06
     Anch
    -0.06
    POSITIVE LOGITS
     wellbeing
    0.09
    GH
    0.07
    TÜRK
    0.07
    ▄
    0.07
     pequeña
    0.07
     rk
    0.07
     previously
    0.07
    kea
    0.07
    他の
    0.07
    ع
    0.07
    Act Density 0.010%

    No Known Activations