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

    Neuronpedia

    INDEX
    Explanations

    and consideration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     consistently
    0.79
    经常
    0.79
    碖
    0.79
     regularly
    0.79
     routinely
    0.77
    Consistency
    0.75
     continually
    0.75
    倛
    0.74
    istently
    0.74
     standart
    0.73
    POSITIVE LOGITS
     interview
    0.81
     overview
    0.71
     Nicholls
    0.70
     interviews
    0.70
     arranque
    0.69
     Interview
    0.69
     overlays
    0.68
     Holman
    0.67
    ibling
    0.66
    मेर
    0.66
    Act Density 0.008%

    No Known Activations