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

    Neuronpedia

    INDEX
    Explanations

    Class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dul
    -0.07
     site
    -0.07
     chica
    -0.07
    _palette
    -0.07
     اتاق
    -0.07
     oscillator
    -0.07
     محیط
    -0.06
    malloc
    -0.06
    Recording
    -0.06
     translation
    -0.06
    POSITIVE LOGITS
     Class
    0.10
    -class
    0.09
    Class
    0.08
    -Class
    0.07
     class
    0.07
     dhe
    0.06
     Took
    0.06
     Curse
    0.06
    sters
    0.06
    NESS
    0.06
    Act Density 0.027%

    No Known Activations