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

    Neuronpedia

    INDEX
    Explanations

    names followed by email

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     বরাবর
    0.41
     oznac
    0.39
     Bot
    0.39
    客服
    0.39
     designates
    0.38
     contribuer
    0.38
     sede
    0.37
     сайты
    0.37
     인사
    0.37
     항
    0.37
    POSITIVE LOGITS
     john
    0.77
    john
    0.76
     daniel
    0.66
     david
    0.63
    michael
    0.63
    david
    0.63
    daniel
    0.63
     james
    0.62
     michael
    0.62
    andrew
    0.62
    Act Density 0.005%

    No Known Activations