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

    Neuronpedia

    INDEX
    Explanations

    the trevor project

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TextAlign
    0.38
    Horizon
    0.37
    ကျ
    0.36
     मालिनी
    0.36
    Kum
    0.36
     розы
    0.35
     ಖರೀದ
    0.34
     Horizon
    0.34
     クリ
    0.34
    𝘇
    0.34
    POSITIVE LOGITS
     Bobby
    0.39
    Bobby
    0.39
     Jud
    0.36
     Bruno
    0.36
     Tunnel
    0.36
    peg
    0.35
    ibur
    0.35
    يسي
    0.35
    Tommy
    0.35
     Pul
    0.34
    Act Density 0.014%

    No Known Activations