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

    Neuronpedia

    INDEX
    Explanations

    variable declaration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     parameters
    -0.07
     δημιουργ
    -0.07
    _epochs
    -0.07
    _functions
    -0.06
    /function
    -0.06
     sınır
    -0.06
    ccoli
    -0.06
     esos
    -0.06
     fluorescence
    -0.06
     Roe
    -0.06
    POSITIVE LOGITS
     ka
    0.07
     mou
    0.07
    ving
    0.06
     şer
    0.06
     hace
    0.06
     massive
    0.06
    /q
    0.06
    �
    0.06
    [R
    0.06
    *@
    0.06
    Act Density 0.034%

    No Known Activations