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

    Neuronpedia

    INDEX
    Explanations

    Everyday tasks and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    렇
    0.45
     herni
    0.44
    itoneal
    0.43
     આનંદ
    0.42
     বিশ্লেষণ
    0.40
    altra
    0.40
    ická
    0.40
    Trailer
    0.39
     Tanık
    0.39
     বৎসরের
    0.39
    POSITIVE LOGITS
     canonical
    0.39
     ome
    0.39
     begin
    0.38
    ไ
    0.37
     classics
    0.37
     bele
    0.37
    ]}
    0.36
    |}
    0.36
    meg
    0.36
    منت
    0.36
    Act Density 0.000%

    No Known Activations