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

    Neuronpedia

    INDEX
    Explanations

    network traffic dwindled

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     スペ
    0.44
     aggress
    0.43
     ジャ
    0.43
    ್ಟ
    0.43
     バック
    0.42
     tonos
    0.42
     barbarian
    0.42
    ધન
    0.42
    蟻
    0.42
     ٹ
    0.42
    POSITIVE LOGITS
    rief
    0.48
     wedi
    0.45
     decomposed
    0.41
    seite
    0.41
    split
    0.40
    ริม
    0.39
     highScore
    0.39
    irer
    0.39
    jekt
    0.38
    readLine
    0.38
    Act Density 0.011%

    No Known Activations