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

    Neuronpedia

    INDEX
    Explanations

    humiliatrix, slave, trade, assume

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ed
    0.49
    us
    0.49
    canic
    0.48
    code
    0.47
    indak
    0.46
    raw
    0.44
    rawdę
    0.43
     Welcome
    0.43
    ac
    0.42
     stained
    0.41
    POSITIVE LOGITS
    Мы
    0.50
    ស្ថ
    0.47
    ༠
    0.45
     정부
    0.45
    Во
    0.44
    今年的
    0.43
     графі
    0.43
    힙
    0.43
     घोटा
    0.43
     Estamos
    0.42
    Act Density 0.005%

    No Known Activations