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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Enum
    -0.07
    泄露
    -0.07
    ambil
    -0.07
    utdown
    -0.06
    تصر
    -0.06
     anlaşma
    -0.06
     oldest
    -0.06
     thập
    -0.06
     finish
    -0.06
    ulkan
    -0.06
    POSITIVE LOGITS
     Sah
    0.07
    样子
    0.07
    مسجد
    0.06
    גידול
    0.06
     dumped
    0.06
     collaborating
    0.06
     vos
    0.06
     collaborators
    0.06
    MO
    0.06
    사항
    0.06
    Act Density 0.016%

    No Known Activations