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

    Neuronpedia

    INDEX
    Explanations

    python modules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    вих
    0.35
    ശന
    0.34
    selves
    0.34
    indsay
    0.33
    REGIUNE
    0.33
    <unused717>
    0.33
     PHILLIPS
    0.32
     Steele
    0.31
    帏
    0.31
    IRONMENT
    0.31
    POSITIVE LOGITS
    ::
    0.32
    utils
    0.31
    Util
    0.30
     ?
    0.29
    Client
    0.28
     utils
    0.28
     tomonidan
    0.27
     create
    0.27
    jo
    0.27
    util
    0.27
    Act Density 0.044%

    No Known Activations