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

    Neuronpedia

    INDEX
    Explanations

    model

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Replace
    -0.08
    .clone
    -0.07
    XA
    -0.07
     CPS
    -0.07
     л
    -0.07
    NonNull
    -0.07
    .cols
    -0.07
    ồi
    -0.07
    昏
    -0.07
     repmat
    -0.07
    POSITIVE LOGITS
     traveller
    0.08
     Boundary
    0.08
    祲
    0.08
    .Course
    0.07
    ":↵↵
    0.07
    ===============
    0.07
    퇼
    0.07
    Statistics
    0.06
    _reading
    0.06
     Laure
    0.06
    Act Density 0.002%

    No Known Activations