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

    Neuronpedia

    INDEX
    Explanations

    openly available weights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    業界
    0.45
     pula
    0.44
    CCNC
    0.44
     JFK
    0.42
     debacle
    0.41
     ఏర్పాటు
    0.41
    装備
    0.40
     منزل
    0.40
     سسٹم
    0.39
     Spectra
    0.39
    POSITIVE LOGITS
     itself
    0.48
    +
    0.45
    의
    0.45
    、
    0.44
     של
    0.44
     của
    0.43
    ке
    0.43
     của
    0.42
    kond
    0.41
    сима
    0.39
    Act Density 0.144%

    No Known Activations