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

    Neuronpedia

    INDEX
    Explanations

    easier access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Statue
    0.52
     Ref
    0.49
     tartalmaz
    0.48
     Circular
    0.46
     detalle
    0.46
     Caixa
    0.46
     Sailor
    0.46
     Maler
    0.46
     её
    0.45
     Produto
    0.45
    POSITIVE LOGITS
    yas
    0.48
    Emphasis
    0.48
    yat
    0.48
    ريس
    0.47
    𒌑
    0.47
    AsUpIndicator
    0.46
    olis
    0.46
    otions
    0.46
    質問
    0.45
    idelijk
    0.45
    Act Density 0.000%

    No Known Activations