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

    Neuronpedia

    INDEX
    Explanations

    list items with examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    वे
    0.46
    IS
    0.44
    An
    0.42
    -
    0.41
     "
    0.40
    其
    0.40
    м
    0.40
    ш
    0.40
    نا
    0.39
    let
    0.39
    POSITIVE LOGITS
     lèvres
    0.62
     halfCanvasWidth
    0.57
     jornalista
    0.55
     dfs
    0.54
     privatisation
    0.54
     belakang
    0.54
     bhfu
    0.54
    amı
    0.54
     customise
    0.54
    0.54
    Act Density 0.000%

    No Known Activations