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

    Neuronpedia

    INDEX
    Explanations

    external links or versions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🫅
    -2.88
    埽
    -2.84
    筇
    -2.50
    圌
    -2.50
    糨
    -2.38
    י
    -2.38
    涠
    -2.30
    蔸
    -2.28
     identifiés
    -2.25
    腘
    -2.25
    POSITIVE LOGITS
    what
    3.00
    ୌ
    2.67
     unparalleled
    2.61
    ization
    2.58
    t
    2.58
     three
    2.50
    lossians
    2.45
    3
    2.44
     tangible
    2.42
     longtime
    2.39
    Act Density 0.013%

    No Known Activations