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

    Neuronpedia

    INDEX
    Explanations

    graph TD

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ίων
    0.46
    並
    0.45
    巨大
    0.41
     consuming
    0.41
    出来る
    0.40
    Encoded
    0.40
    見
    0.39
     regiones
    0.39
     consumption
    0.39
    重启
    0.39
    POSITIVE LOGITS
    urence
    0.49
     приветствую
    0.47
     ረ
    0.46
    Lam
    0.44
    ancouver
    0.43
    ന
    0.43
    ah
    0.43
     упа
    0.43
    n
    0.42
     pozy
    0.42
    Act Density 0.001%

    No Known Activations