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

    Neuronpedia

    INDEX
    Explanations

    life, larvae, munitions, history

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jun
    0.45
     Frances
    0.42
     Src
    0.42
     syscall
    0.41
     rtl
    0.41
     Har
    0.40
     francs
    0.40
     Max
    0.39
     blanca
    0.39
     дополнительные
    0.38
    POSITIVE LOGITS
    вання
    0.51
    vers
    0.48
    ONES
    0.46
    INGO
    0.46
    ING
    0.45
    ৩৫
    0.45
    साठी
    0.45
    VERN
    0.44
    GER
    0.43
     შორის
    0.43
    Act Density 0.000%

    No Known Activations