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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     besteht
    -0.07
    امت
    -0.07
    疢
    -0.07
     auto
    -0.06
     stratég
    -0.06
     ép
    -0.06
     outbreaks
    -0.06
     Subcommittee
    -0.06
    龂
    -0.06
    attr
    -0.06
    POSITIVE LOGITS
    (errorMessage
    0.08
    信
    0.07
    hwnd
    0.07
     cowork
    0.07
    潜能
    0.07
     flat
    0.07
    iconductor
    0.07
     moderators
    0.07
    Destroyed
    0.07
     png
    0.07
    Act Density 0.001%

    No Known Activations