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

    Neuronpedia

    INDEX
    Explanations

    bot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alore
    -0.08
    UIViewController
    -0.07
     Baths
    -0.07
    (DbContext
    -0.07
    @
    -0.07
    DL
    -0.07
    ondo
    -0.07
    vey
    -0.07
    ANNOT
    -0.07
     /\.(
    -0.06
    POSITIVE LOGITS
     выгод
    0.08
    	RE
    0.08
     eigenen
    0.07
    群体
    0.07
    奴隶
    0.07
     الحكوم
    0.07
    Participant
    0.07
     السلطة
    0.07
     >(
    0.07
     simplement
    0.07
    Act Density 0.008%

    No Known Activations