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

    Neuronpedia

    INDEX
    Explanations

    из

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     schn
    -0.08
     surrender
    -0.08
     себ
    -0.07
    Prompt
    -0.07
     temper
    -0.07
     bump
    -0.07
     phenomenal
    -0.07
     венти
    -0.07
     Spend
    -0.06
     embar
    -0.06
    POSITIVE LOGITS
     из
    0.16
     aus
    0.12
     Из
    0.10
    Из
    0.10
    из
    0.09
     from
    0.09
    .avg
    0.08
    Aus
    0.08
    .ImageIcon
    0.07
    US
    0.07
    Act Density 0.017%

    No Known Activations