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

    Neuronpedia

    INDEX
    Explanations

    offering help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OE
    1.30
    I
    1.28
     woven
    1.18
    selves
    1.14
    狨
    1.13
    岖
    1.11
     colored
    1.09
    нд
    1.09
     Jenis
    1.08
    ladı
    1.07
    POSITIVE LOGITS
    о
    1.48
     đỡ
    1.40
    ం
    1.18
     оказалось
    1.14
    ول
    1.13
     ích
    1.13
    і
    1.12
    ная
    1.09
    ून
    1.07
    newBuilder
    1.05
    Act Density 0.107%

    No Known Activations