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

    Neuronpedia

    INDEX
    Explanations

    dressing modestly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stance
    0.64
     dram
    0.57
     grams
    0.57
     modem
    0.56
     spond
    0.52
     lept
    0.52
     historical
    0.51
     keyst
    0.51
    0.51
     pseud
    0.51
    POSITIVE LOGITS
    و
    0.53
    ো
    0.51
    navigate
    0.50
    ée
    0.48
    с
    0.48
    servers
    0.48
    一个
    0.47
    特别是
    0.47
    église
    0.47
    departments
    0.47
    Act Density 0.000%

    No Known Activations