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

    Neuronpedia

    INDEX
    Explanations

    anecdotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     coax
    -0.07
     offender
    -0.06
    _distance
    -0.06
     effort
    -0.06
    tober
    -0.06
     Accord
    -0.06
     manifested
    -0.06
    03
    -0.06
    _SPLIT
    -0.06
    06
    -0.06
    POSITIVE LOGITS
     ´
    0.07
     mutlu
    0.06
    αρα
    0.06
     href
    0.06
     بازی
    0.06
     المدر
    0.06
     "{$
    0.06
    まる
    0.06
    อากาศ
    0.06
     "".
    0.06
    Act Density 0.095%

    No Known Activations