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

    Neuronpedia

    INDEX
    Explanations

    code and cryptography parameters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ahmed
    -0.07
     shakes
    -0.06
    ечение
    -0.06
     hộ
    -0.06
    _sec
    -0.06
     regular
    -0.06
     $$$
    -0.06
    _HASH
    -0.06
     sollte
    -0.06
    KT
    -0.06
    POSITIVE LOGITS
    /payment
    0.07
    }")
    0.07
    uyla
    0.06
    internal
    0.06
    stderr
    0.06
    _Click
    0.06
     Savior
    0.06
    	RTCK
    0.06
    WebResponse
    0.06
    اصل
    0.06
    Act Density 0.004%

    No Known Activations