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

    Neuronpedia

    INDEX
    Explanations

    explaining, outlining, describing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     într
    0.42
    已经在
    0.39
    被人
    0.38
     যখন
    0.38
     সম্মুখীন
    0.38
    ผ่าน
    0.37
     работают
    0.37
     бывают
    0.37
     và
    0.36
     agus
    0.36
    POSITIVE LOGITS
     describing
    1.11
     explaining
    1.07
     indicating
    1.01
     outlining
    1.01
     indiquant
    0.97
     detailing
    0.90
     specifying
    0.89
     explicando
    0.86
    indicating
    0.83
     stating
    0.82
    Act Density 0.155%

    No Known Activations