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

    Neuronpedia

    INDEX
    Explanations

    Print-on-Demand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fach
    0.62
    𝐬
    0.62
    Enfin
    0.57
    opener
    0.57
     ega
    0.56
    𝐭
    0.55
    𝓉
    0.55
    টিউ
    0.55
    tedir
    0.55
    établir
    0.54
    POSITIVE LOGITS
    idation
    0.41
     shop
    0.39
     show
    0.39
     lives
    0.38
     skillful
    0.36
     brilliance
    0.35
     feat
    0.35
     z
    0.35
     beach
    0.35
    ,
    0.35
    Act Density 0.003%

    No Known Activations