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

    Neuronpedia

    INDEX
    Explanations

    start of revolutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     infidelity
    0.46
     prints
    0.43
    δου
    0.43
     bitmap
    0.43
    ونی
    0.41
    mma
    0.41
     tele
    0.41
     intoler
    0.41
     irritability
    0.41
    ен
    0.40
    POSITIVE LOGITS
     Forder
    0.46
    icron
    0.46
    pei
    0.45
     Approved
    0.45
     البيت
    0.45
     တော့
    0.45
     GRAPH
    0.44
     TIME
    0.43
     HALL
    0.43
    的就是
    0.43
    Act Density 0.000%

    No Known Activations