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

    Neuronpedia

    INDEX
    Explanations

    degree

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    resources
    -0.08
    Strange
    -0.07
     gov
    -0.07
     "@/
    -0.07
    Reservation
    -0.07
    )}.
    -0.07
    	state
    -0.06
     zřejmě
    -0.06
     \@
    -0.06
    /chat
    -0.06
    POSITIVE LOGITS
     Hers
    0.07
    fection
    0.07
     Jer
    0.06
    ouser
    0.06
     Fauc
    0.06
    BundleOrNil
    0.06
    iterated
    0.06
     perpetrated
    0.06
     discre
    0.06
    ilmiş
    0.06
    Act Density 0.010%

    No Known Activations