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

    Neuronpedia

    INDEX
    Explanations

    light

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Developed
    -0.07
     SEX
    -0.06
     esc
    -0.06
    $date
    -0.06
    apatkan
    -0.06
    radu
    -0.06
     natürlich
    -0.06
     температу
    -0.06
     Dice
    -0.06
     wollte
    -0.06
    POSITIVE LOGITS
    梅
    0.07
     pj
    0.07
    ㆍ동
    0.06
     Jay
    0.06
     Allocate
    0.06
    ौं
    0.06
    ':↵↵
    0.06
    IndexOf
    0.06
     enumerator
    0.06
     elle
    0.06
    Act Density 0.004%

    No Known Activations