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
     zemí
    -0.06
    юн
    -0.06
     turning
    -0.06
    elage
    -0.06
     Diss
    -0.06
    Close
    -0.06
     fortress
    -0.06
     chancellor
    -0.06
    kas
    -0.05
     lun
    -0.05
    POSITIVE LOGITS
    /use
    0.07
     ομά
    0.07
     Moments
    0.07
    redict
    0.07
     DataRow
    0.07
     позд
    0.06
     frankly
    0.06
    POCH
    0.06
    grams
    0.06
     ########.
    0.06
    Act Density 0.000%

    No Known Activations