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

    Neuronpedia

    INDEX
    Explanations

    production deployment, public reports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    皞
    0.51
     Tekh
    0.47
    闶
    0.47
    笕
    0.46
     RxSwift
    0.45
    ሆኑ
    0.44
     secretions
    0.44
    㜖
    0.43
     医学
    0.43
    elementProp
    0.43
    POSITIVE LOGITS
    and
    0.44
     S
    0.43
    b
    0.43
    nu
    0.40
    sc
    0.39
    admins
    0.38
    -.
    0.38
    j
    0.38
    lene
    0.38
    eca
    0.37
    Act Density 0.001%

    No Known Activations