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

    Neuronpedia

    INDEX
    Explanations

    concepts followed by punctuation or description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defini
    0.47
     पढ़े
    0.47
    ഗീയ
    0.43
    อล
    0.43
    Always
    0.43
     פר
    0.43
     zd
    0.42
    Personal
    0.42
     ziet
    0.42
     fortale
    0.41
    POSITIVE LOGITS
    脿
    0.50
    ものである
    0.48
     Planting
    0.48
     anaemia
    0.47
    嚆
    0.47
    orsese
    0.47
     embarazada
    0.47
     डीपी
    0.46
    ایی
    0.46
    atures
    0.46
    Act Density 0.001%

    No Known Activations