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

    Neuronpedia

    INDEX
    Explanations

    t

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     אין
    0.83
    grabbing
    0.82
     grabbing
    0.76
    ꞌ
    0.76
     나왔
    0.76
     heinous
    0.74
    diving
    0.74
     く
    0.74
     scraper
    0.73
     ignorance
    0.72
    POSITIVE LOGITS
     spend
    0.87
     bother
    0.83
     be
    0.80
     legislate
    0.74
     judge
    0.72
     worry
    0.72
     mind
    0.71
    Spend
    0.70
     fret
    0.70
     pay
    0.68
    Act Density 0.066%

    No Known Activations