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

    Neuronpedia

    INDEX
    Explanations

    JSON responses with messages or errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    技术的
    0.38
    iomanip
    0.37
    Mountains
    0.36
    玮
    0.36
    Isaac
    0.36
     помогает
    0.35
    䡉
    0.35
     বিকল্প
    0.35
    Isometric
    0.35
    Ellipse
    0.35
    POSITIVE LOGITS
     message
    0.77
    message
    0.70
     mensaje
    0.69
     messaggio
    0.66
     mesaj
    0.59
     messages
    0.59
     mensagem
    0.59
    メッセージ
    0.58
    msg
    0.57
     msg
    0.57
    Act Density 0.011%

    No Known Activations