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

    Neuronpedia

    INDEX
    Explanations

    Designing, writing, planning novel plots

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disregarded
    0.45
     Keluarga
    0.42
     sejumlah
    0.42
     ignores
    0.42
     মোঃ
    0.41
     faithfully
    0.41
     ignored
    0.40
     appointees
    0.40
     tubuh
    0.38
    ੋ
    0.38
    POSITIVE LOGITS
    صميم
    0.52
    Designing
    0.50
     designing
    0.48
    仕上げ
    0.46
     coraz
    0.46
     Writing
    0.45
     classmates
    0.44
     Designing
    0.44
    মাকে
    0.42
    新しい
    0.41
    Act Density 0.002%

    No Known Activations