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

    Neuronpedia

    INDEX
    Explanations

    discretionary failure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aneur
    0.54
     annex
    0.52
     own
    0.50
     arrhythmia
    0.50
     skle
    0.49
     naszym
    0.49
     shot
    0.49
     discounts
    0.48
     isomer
    0.48
     annexation
    0.48
    POSITIVE LOGITS
    Version
    0.46
    ariant
    0.46
    Мо
    0.46
    Пер
    0.45
    élev
    0.44
     Teaching
    0.44
    Teach
    0.43
    Но
    0.43
    ImageBeforeText
    0.42
    Jason
    0.42
    Act Density 0.000%

    No Known Activations