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

    Neuronpedia

    INDEX
    Explanations

    MAKE

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     audits
    -0.07
     малень
    -0.07
    :invoke
    -0.06
    Florida
    -0.06
     گفت
    -0.06
     criticism
    -0.06
    TEXT
    -0.06
    LOTS
    -0.06
     ніби
    -0.06
     kod
    -0.06
    POSITIVE LOGITS
     CharSet
    0.07
     alignItems
    0.06
     Firearms
    0.06
    Chain
    0.06
    _DEPTH
    0.05
     aur
    0.05
    adı
    0.05
     ин
    0.05
    DEC
    0.05
     ткани
    0.05
    Act Density 0.009%

    No Known Activations