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

    Neuronpedia

    INDEX
    Explanations

    furnished

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fav
    -0.08
    	tv
    -0.07
     demonstration
    -0.07
    .Priority
    -0.07
     destinationViewController
    -0.07
    إز
    -0.07
     vra
    -0.07
     obras
    -0.06
    [g
    -0.06
     representatives
    -0.06
    POSITIVE LOGITS
     Maryland
    0.08
    ожно
    0.07
     Mechanics
    0.07
    Originally
    0.07
     Nightmare
    0.07
     Gardner
    0.07
     HOLDERS
    0.07
    מדיה
    0.07
     Kush
    0.07
    _HE
    0.07
    Act Density 0.102%

    No Known Activations