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

    Neuronpedia

    INDEX
    Explanations

    WPA2/WPA3 security

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᐳ
    0.46
    طات
    0.43
     science
    0.42
     indeed
    0.40
     medicina
    0.40
     Science
    0.39
     Schott
    0.39
     गोप
    0.39
    気になる
    0.38
    गिंग
    0.38
    POSITIVE LOGITS
     Kew
    0.53
     kew
    0.52
    ew
    0.47
    arna
    0.47
    lau
    0.43
    ajib
    0.42
    akili
    0.40
    苾
    0.40
     обязан
    0.39
     millis
    0.39
    Act Density 0.001%

    No Known Activations