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

    Neuronpedia

    INDEX
    Explanations

    clarifying concepts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.07
    ثار
    -0.07
    67
    -0.07
    paste
    -0.06
     Sigma
    -0.06
    _legacy
    -0.06
    ству
    -0.06
    илися
    -0.06
     predictions
    -0.06
     Detect
    -0.06
    POSITIVE LOGITS
    :".$
    0.07
    (IDC
    0.06
     péri
    0.06
    >${
    0.06
    ufreq
    0.06
    .level
    0.06
    [::-
    0.06
    aring
    0.06
     QImage
    0.06
     древ
    0.06
    Act Density 0.045%

    No Known Activations