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

    Neuronpedia

    INDEX
    Explanations

    col followed by suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     column
    0.84
    column
    0.73
    Column
    0.73
     Column
    0.67
     columns
    0.65
     coluna
    0.63
     колон
    0.61
     COLUMN
    0.60
    columns
    0.59
     columnas
    0.57
    POSITIVE LOGITS
    ores
    0.58
    lores
    0.43
    oes
    0.43
     பட்ட
    0.42
    osilicate
    0.42
    ours
    0.40
     Lorentzian
    0.39
    ورس
    0.38
    くなり
    0.37
     Maj
    0.37
    Act Density 0.003%

    No Known Activations