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

    Neuronpedia

    INDEX
    Explanations

    TM)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     нар
    0.38
     arm
    0.37
     readiness
    0.37
     ladder
    0.36
     Nxf
    0.35
     Whisper
    0.35
    рованы
    0.34
     ready
    0.34
     potato
    0.34
     detractors
    0.33
    POSITIVE LOGITS
     spør
    0.44
     قوس
    0.41
     మీడి
    0.40
    ป่วย
    0.40
     ماشي
    0.39
    的神
    0.39
    ร้าย
    0.39
    )"
    0.39
     gospod
    0.39
     გარ
    0.39
    Act Density 0.000%

    No Known Activations