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

    Neuronpedia

    INDEX
    Explanations

    single

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cervical
    -0.07
     fragile
    -0.07
     silently
    -0.07
     Twig
    -0.07
    Votre
    -0.06
    adığ
    -0.06
     confessed
    -0.06
     ฉ
    -0.06
     soğ
    -0.06
    degrees
    -0.06
    POSITIVE LOGITS
    ые
    0.06
     шляхом
    0.06
     Mayweather
    0.06
    elleicht
    0.06
     рішення
    0.06
    uestas
    0.06
    مول
    0.06
     TAX
    0.06
    umably
    0.06
     Bowl
    0.06
    Act Density 0.021%

    No Known Activations