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

    Neuronpedia

    INDEX
    Explanations

    open-weights model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     renormalization
    0.50
     semantics
    0.46
     arbitrage
    0.44
     polysaccharide
    0.44
     invariance
    0.44
     corticosteroids
    0.42
     seasonings
    0.42
     peptides
    0.42
     sterilization
    0.42
     steril
    0.42
    POSITIVE LOGITS
    ificante
    0.48
    answ
    0.47
    agne
    0.46
    चार्य
    0.45
    uner
    0.44
     ይህም
    0.43
    नौ
    0.43
     konkrét
    0.42
     gespre
    0.42
    ей
    0.42
    Act Density 0.027%

    No Known Activations