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

    Neuronpedia

    INDEX
    Explanations

    client/server/proxy interactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    chris
    0.37
     Chris
    0.36
     topping
    0.35
    europa
    0.35
     Rhine
    0.35
     heyday
    0.35
    经常
    0.34
    راجعه
    0.34
     purchasing
    0.34
    伐
    0.34
    POSITIVE LOGITS
    サーバ
    0.44
    ับ
    0.44
    ველი
    0.41
    ंसा
    0.40
    Proxy
    0.40
    ಂತರ
    0.39
    markers
    0.38
    蛛
    0.38
     buona
    0.38
    共通
    0.38
    Act Density 0.000%

    No Known Activations