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

    Neuronpedia

    INDEX
    Explanations

    statistical correlation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     descendants
    -0.06
     Sour
    -0.06
     (↵↵
    -0.06
     Std
    -0.06
     orgasm
    -0.06
    ：↵
    -0.06
     Temple
    -0.06
     repetition
    -0.06
     qr
    -0.06
    leşik
    -0.06
    POSITIVE LOGITS
    creature
    0.08
     comprising
    0.07
    _STR
    0.07
    担当
    0.06
     Spir
    0.06
     featuring
    0.06
    ytt
    0.06
    	it
    0.06
    _Il
    0.06
     controversies
    0.06
    Act Density 0.024%

    No Known Activations