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

    Neuronpedia

    INDEX
    Explanations

    [

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     нос
    -0.06
    (_)
    -0.06
     Jenny
    -0.06
    Poly
    -0.06
     доз
    -0.06
    stdexcept
    -0.06
     physician
    -0.06
    prenom
    -0.06
    forcements
    -0.06
     Tf
    -0.06
    POSITIVE LOGITS
    ंग
    0.07
     '../../../../
    0.07
    […
    0.06
    .att
    0.06
    klass
    0.06
     adversary
    0.06
    asca
    0.06
    jsc
    0.06
     ordin
    0.06
    	flag
    0.06
    Act Density 0.002%

    No Known Activations