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

    Neuronpedia

    INDEX
    Explanations

    CFG scale, sampling, steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bras
    0.41
     attachments
    0.40
    物件
    0.39
     Tuning
    0.38
    urses
    0.37
    硒
    0.37
     bras
    0.37
    附件
    0.37
     Nellie
    0.37
    positions
    0.37
    POSITIVE LOGITS
    动漫
    0.45
     CF
    0.45
     cfg
    0.42
    KF
    0.41
    Sampling
    0.39
    cfg
    0.39
     Euler
    0.38
    CF
    0.38
    Guid
    0.38
    sampling
    0.38
    Act Density 0.013%

    No Known Activations