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

    Neuronpedia

    INDEX
    Explanations

    good for beginners or specific situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     võimalik
    0.36
    engono
    0.35
    ❁
    0.33
     (\%)
    0.33
    TWO
    0.33
     mögliche
    0.32
    误差
    0.31
    tenths
    0.31
    *\
    0.31
    error
    0.30
    POSITIVE LOGITS
     beginners
    0.83
     anyone
    0.70
     situations
    0.66
     quick
    0.65
     Beginners
    0.62
     когда
    0.61
     general
    0.61
     quickly
    0.59
     beginner
    0.58
     when
    0.57
    Act Density 0.077%

    No Known Activations