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

    Neuronpedia

    INDEX
    Explanations

    message specific actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    搭載
    0.41
     erecting
    0.39
     obten
    0.38
    setColor
    0.38
     paddling
    0.38
    ra
    0.38
     कड़ी
    0.37
     democratic
    0.36
    pectral
    0.36
     جال
    0.36
    POSITIVE LOGITS
    Kafka
    0.52
     zusätzliche
    0.51
    Send
    0.46
     adaptador
    0.45
     Streaming
    0.43
     tarifs
    0.43
    Socket
    0.43
     Send
    0.43
    滤波
    0.43
     दरों
    0.42
    Act Density 0.000%

    No Known Activations