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

    Neuronpedia

    INDEX
    Explanations

    times and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    يش
    0.64
     fires
    0.64
    ાળ
    0.62
    题
    0.62
     maî
    0.61
     Bache
    0.61
    栈
    0.61
     IPython
    0.61
     joking
    0.60
    ના
    0.59
    POSITIVE LOGITS
    D
    0.81
     systems
    0.78
    ᴰ
    0.75
     سیستم
    0.71
     system
    0.70
     نظام
    0.70
     collega
    0.69
    Ds
    0.69
    णाऱ्या
    0.69
    ដឹក
    0.69
    Act Density 0.057%

    No Known Activations