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

    Neuronpedia

    INDEX
    Explanations

    -g

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ificar
    -0.08
    CGColor
    -0.07
     prá
    -0.07
     sees
    -0.07
     hum
    -0.07
    _recv
    -0.07
    حرص
    -0.06
     encourages
    -0.06
     enraged
    -0.06
    乃至
    -0.06
    POSITIVE LOGITS
     undisclosed
    0.07
    حلة
    0.07
    身躯
    0.07
    RICT
    0.07
     Minutes
    0.07
     DRIVER
    0.07
     Estimated
    0.07
     catégorie
    0.07
    PN
    0.07
     urine
    0.07
    Act Density 0.001%

    No Known Activations