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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alım
    -0.07
    _faces
    -0.07
    eggies
    -0.07
     dokonce
    -0.07
     некотор
    -0.06
    Keep
    -0.06
     prognosis
    -0.06
    ampions
    -0.06
    히
    -0.06
     Rankings
    -0.06
    POSITIVE LOGITS
    _beta
    0.06
    ISTER
    0.06
     يا
    0.06
     kill
    0.06
     baş
    0.06
     bowl
    0.06
    -ag
    0.06
     conserv
    0.06
     Wise
    0.06
     قال
    0.06
    Act Density 0.001%

    No Known Activations