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

    Neuronpedia

    INDEX
    Explanations

    specific entities or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ्यूस
    0.45
     데이터를
    0.42
     painfully
    0.41
     swells
    0.39
     UNNEEDED
    0.39
    ствовали
    0.38
    ሂ
    0.38
    饷
    0.38
     klein
    0.38
     bung
    0.38
    POSITIVE LOGITS
    Ry
    0.41
    ★★★
    0.40
    Peter
    0.40
    Christopher
    0.40
     restant
    0.39
    Sh
    0.39
    ș
    0.38
     στους
    0.38
    PDF
    0.38
     ಉಳ
    0.38
    Act Density 0.000%

    No Known Activations