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

    Neuronpedia

    INDEX
    Explanations

    ne

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dir
    -0.06
    Rejected
    -0.06
     cps
    -0.06
    >R
    -0.06
    كيل
    -0.06
     mild
    -0.06
     Eld
    -0.06
    849
    -0.06
    _algorithm
    -0.06
     stylist
    -0.06
    POSITIVE LOGITS
    ne
    0.13
    NE
    0.09
    né
    0.09
    unce
    0.08
    orne
    0.07
     NE
    0.07
     Те
    0.07
    n
    0.07
    ่วน
    0.07
     carcin
    0.07
    Act Density 0.028%

    No Known Activations