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
     během
    -0.07
    생님
    -0.07
    .available
    -0.06
     Cand
    -0.06
    replaceAll
    -0.06
    東京
    -0.06
    uyên
    -0.06
     часом
    -0.06
    nga
    -0.06
    ्पत
    -0.06
    POSITIVE LOGITS
    must
    0.08
     Grape
    0.07
    全球
    0.07
    _cats
    0.06
     empt
    0.06
    bones
    0.06
     mammals
    0.06
     별
    0.06
     맡
    0.06
    	ff
    0.06
    Act Density 0.000%

    No Known Activations