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

    Neuronpedia

    INDEX
    Explanations

    To

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pavement
    -0.06
    category
    -0.06
     jeopardy
    -0.06
     север
    -0.06
    них
    -0.06
    оск
    -0.06
     religious
    -0.06
    (dw
    -0.06
    "]=="
    -0.06
    河
    -0.06
    POSITIVE LOGITS
    To
    0.07
     RedirectTo
    0.06
     u
    0.06
    λλα
    0.06
    ์,
    0.06
     bổ
    0.06
    udiantes
    0.06
    与
    0.06
    _to
    0.06
    ühl
    0.06
    Act Density 0.015%

    No Known Activations