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

    Neuronpedia

    INDEX
    Explanations

    technical documents with equations and figures

    oai_token-act-pair · gemini-2.0-flash

    scientific/mathematical formulas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UnsafeEnabled
    -0.57
     EnglishChoose
    -0.55
     Kidman
    -0.53
    contentLoaded
    -0.52
    styleable
    -0.52
     Haywood
    -0.51
    AutoScaleMode
    -0.51
     szolg
    -0.50
     ویکی‌پدیا
    -0.50
     glaucoma
    -0.49
    POSITIVE LOGITS
     Tt
    0.59
     dE
    0.54
     σ
    0.53
     Dp
    0.53
     rr
    0.52
     Ea
    0.51
     Ii
    0.50
     KK
    0.50
     ɛ
    0.50
     Rn
    0.49
    Act Density 46.674%

    No Known Activations