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

    Neuronpedia

    INDEX
    Explanations

    comm or com continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     decent
    0.71
     stems
    0.70
     hears
    0.69
     watered
    0.68
    ため
    0.67
     sounded
    0.67
     sounds
    0.66
     nutty
    0.66
     lighter
    0.66
     harsh
    0.66
    POSITIVE LOGITS
    unication
    1.36
    unicaciones
    1.18
    unications
    1.16
    UNIC
    1.11
    ്യൂ
    1.05
    posto
    0.97
    plemented
    0.97
    prising
    0.96
    commentaire
    0.93
    prehensive
    0.93
    Act Density 0.051%

    No Known Activations