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

    Neuronpedia

    INDEX
    Explanations

    4 oz measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鿢
    0.44
    baseline
    0.43
     quelqu
    0.43
    lemens
    0.42
    叒
    0.42
     baz
    0.41
    軺
    0.41
    емый
    0.40
     ادائیگی
    0.40
    駭
    0.40
    POSITIVE LOGITS
     sparse
    0.38
     affords
    0.35
     SP
    0.34
    ノート
    0.34
     Venice
    0.33
     virtues
    0.33
     complications
    0.33
     )
    0.32
    alah
    0.32
    LAY
    0.32
    Act Density 0.001%

    No Known Activations