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

    Neuronpedia

    INDEX
    Explanations

    programming keywords and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᅡ
    0.28
    張
    0.27
    ToCheck
    0.26
    ulfonic
    0.22
    מת
    0.22
    が
    0.22
    \}$.
    0.21
     గో
    0.21
    羹
    0.21
     获取
    0.21
    POSITIVE LOGITS
    writeFileSync
    0.24
    llen
    0.24
     puisqu
    0.24
     நாங்கள்
    0.23
    setEmail
    0.23
     Leno
    0.22
     senang
    0.22
     oma
    0.22
     Majesty
    0.21
    द्दी
    0.21
    Act Density 0.184%

    No Known Activations