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

    Neuronpedia

    INDEX
    Explanations

    Connecting phrases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bmp
    -0.07
     k
    -0.07
     relocated
    -0.07
    >())↵
    -0.06
     identifiers
    -0.06
    .margin
    -0.06
     Employment
    -0.06
    ’t
    -0.06
    Floating
    -0.06
    __.
    -0.06
    POSITIVE LOGITS
    すべて
    0.07
    losion
    0.06
    developers
    0.06
     diffs
    0.06
     sticky
    0.06
    ":"","
    0.06
     sẵn
    0.06
    Vectors
    0.06
     máy
    0.06
    _dash
    0.06
    Act Density 0.144%

    No Known Activations