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

    Neuronpedia

    INDEX
    Explanations

    phase II detoxification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /hr
    -0.08
    notif
    -0.08
    (hr
    -0.07
     bann
    -0.07
     霍
    -0.07
    scribed
    -0.07
     اطلاع
    -0.07
     billi
    -0.07
     cair
    -0.07
     pacing
    -0.07
    POSITIVE LOGITS
     detox
    0.13
     Detox
    0.11
     sunscreen
    0.09
     pesticides
    0.08
     kufanya
    0.08
     Schne
    0.08
     defens
    0.08
     detergent
    0.08
     cosmetics
    0.08
     Sob
    0.08
    Act Density 0.003%

    No Known Activations