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

    Neuronpedia

    INDEX
    Explanations

    Stable Diffusion model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     essay
    0.40
     password
    0.39
     Essay
    0.38
     portion
    0.36
     merci
    0.36
     мол
    0.36
    ğer
    0.36
     geral
    0.36
     fascination
    0.36
     Don
    0.36
    POSITIVE LOGITS
    ্সা
    0.42
    irms
    0.42
    BACKGROUND
    0.42
    フル
    0.41
    ksjon
    0.39
    ⺈
    0.39
    బాటు
    0.39
    procedures
    0.39
     Durchführung
    0.39
    candidate
    0.38
    Act Density 0.005%

    No Known Activations