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

    Neuronpedia

    INDEX
    Explanations

    if statements with conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     وقتی
    0.55
    Cómo
    0.51
     таксама
    0.48
    vitamin
    0.48
     دوسرا
    0.48
    代謝
    0.47
    代谢
    0.47
    维生素
    0.47
    浲
    0.46
    Dopo
    0.46
    POSITIVE LOGITS
     isn
    0.79
     hasattr
    0.77
     isinstance
    0.77
     is
    0.75
     !
    0.72
     that
    0.68
     it
    0.68
     (!
    0.67
     !=
    0.65
     !(
    0.64
    Act Density 0.057%

    No Known Activations