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

    Neuronpedia

    INDEX
    Explanations

    wire connectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     esport
    0.40
    汉
    0.40
     malattie
    0.39
    крови
    0.39
    tans
    0.37
     黄
    0.36
    edian
    0.36
     К
    0.36
     হৃদ
    0.36
     danni
    0.36
    POSITIVE LOGITS
    N
    0.43
    VN
    0.42
    ْن
    0.39
    Multiline
    0.38
    żeli
    0.37
    itteln
    0.37
    EL
    0.36
    FileSync
    0.36
    ZM
    0.36
     booming
    0.36
    Act Density 0.003%

    No Known Activations