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

    Neuronpedia

    INDEX
    Explanations

    as inputs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ज्ञापन
    0.44
     डिटेल्स
    0.40
    decoder
    0.39
     requester
    0.39
    Decoder
    0.38
    หน้าที่
    0.38
    ನ
    0.38
     larga
    0.37
    钒
    0.37
    ላት
    0.37
    POSITIVE LOGITS
     mode
    0.41
    抟
    0.38
    引っ
    0.38
    mode
    0.36
    ève
    0.36
    ربه
    0.36
     سرا
    0.36
    opausal
    0.36
     gelt
    0.35
     concurrence
    0.34
    Act Density 0.003%

    No Known Activations