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

    Neuronpedia

    INDEX
    Explanations

    struggling

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     troubles
    0.75
     problemy
    0.74
     Combat
    0.72
     problems
    0.70
     trouble
    0.69
     Tonight
    0.69
     Problems
    0.68
     proble
    0.67
     đây
    0.67
     problémy
    0.66
    POSITIVE LOGITS
     extends
    0.73
     ሚ
    0.70
     becomes
    0.69
     became
    0.68
    eggs
    0.68
     обладает
    0.68
    became
    0.68
     emotionally
    0.67
    covers
    0.65
     লাগে
    0.65
    Act Density 0.020%

    No Known Activations