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

    Neuronpedia

    INDEX
    Explanations

    programmed to be safe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uyentes
    0.42
     জুল
    0.42
     ज्वालामुखी
    0.41
    Amber
    0.41
    jupiter
    0.38
     bim
    0.38
    蛟
    0.38
    マリ
    0.37
     Rens
    0.37
    Viv
    0.36
    POSITIVE LOGITS
    ड्रो
    0.42
    款
    0.40
    провод
    0.39
    строен
    0.39
     Wada
    0.39
     Osten
    0.38
     asymmetry
    0.38
     asymmetric
    0.37
    кет
    0.37
    строи
    0.37
    Act Density 0.010%

    No Known Activations