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

    Neuronpedia

    INDEX
    Explanations

    welcome greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mam
    0.43
     واجب
    0.43
    GFS
    0.42
    ZF
    0.40
     Mam
    0.39
    find
    0.39
     ضرورت
    0.38
    pink
    0.37
    mam
    0.37
     مختلف
    0.36
    POSITIVE LOGITS
     symbolTable
    0.49
    蛉
    0.42
     expériment
    0.41
     неста
    0.41
    ваться
    0.40
     Airlines
    0.40
    AutoHide
    0.39
     mê
    0.39
    леге
    0.38
    fton
    0.38
    Act Density 0.000%

    No Known Activations