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

    Neuronpedia

    INDEX
    Explanations

    after, half, over, in, all, best, around

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     সাথে
    0.59
    as
    0.56
    াই
    0.51
    서
    0.51
    mmmm
    0.50
     всі
    0.49
    jenigen
    0.49
    সাথে
    0.48
    ри
    0.47
    跶
    0.47
    POSITIVE LOGITS
    -
    0.66
     defunct
    0.46
    -,
    0.45
    lings
    0.45
    ings
    0.44
     tangible
    0.44
    ional
    0.42
    lashes
    0.42
    comers
    0.41
     deliberation
    0.41
    Act Density 0.000%

    No Known Activations