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

    Neuronpedia

    INDEX
    Explanations

    say "grind" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    рь
    -0.07
    444
    -0.06
    TE
    -0.06
    anking
    -0.06
    307
    -0.06
    757
    -0.06
     toutes
    -0.06
     toàn
    -0.06
    Audio
    -0.06
     بانک
    -0.06
    POSITIVE LOGITS
    صب
    0.07
    $text
    0.07
    queueReusableCell
    0.07
    сутств
    0.07
    oretical
    0.06
     patents
    0.06
     defin
    0.06
    _THEME
    0.06
     season
    0.06
    Installed
    0.06
    Act Density 0.052%

    No Known Activations