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

    Neuronpedia

    INDEX
    Explanations

    specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lapangan
    0.52
     возбу
    0.49
     Dalmat
    0.49
    咟
    0.47
     Кири
    0.47
     архитек
    0.46
     bahagia
    0.46
     радо
    0.46
     Bahrain
    0.46
     huj
    0.46
    POSITIVE LOGITS
     physicality
    0.42
    pps
    0.41
    oplasm
    0.41
     perfecting
    0.40
    〆
    0.40
     MON
    0.39
    icer
    0.38
    DEG
    0.38
    ausch
    0.38
     completeness
    0.38
    Act Density 0.000%

    No Known Activations