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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DLL
    -0.07
     Positive
    -0.07
     flipping
    -0.07
    _load
    -0.07
     Naughty
    -0.07
     OnTrigger
    -0.06
    享
    -0.06
    mscorlib
    -0.06
     pend
    -0.06
     sick
    -0.06
    POSITIVE LOGITS
     perfil
    0.07
     필요
    0.07
     بیم
    0.07
    ๑
    0.06
    Traditional
    0.06
    кування
    0.06
     birthdays
    0.06
    _agg
    0.06
    áv
    0.06
     rigorous
    0.06
    Act Density 0.008%

    No Known Activations