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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scrub
    -0.07
     census
    -0.07
    asso
    -0.06
    Hospital
    -0.06
     fees
    -0.06
    .tax
    -0.06
    hetto
    -0.06
    -floor
    -0.06
     віднов
    -0.06
    .ID
    -0.06
    POSITIVE LOGITS
     했다
    0.07
     Px
    0.07
     Một
    0.07
     مدل
    0.07
    �다
    0.07
    >").
    0.07
     demek
    0.07
    ा.
    0.07
    ;:
    0.06
     عملية
    0.06
    Act Density 0.026%

    No Known Activations