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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    응
    -0.07
    ุส
    -0.06
     consumes
    -0.06
     queryString
    -0.06
    男人
    -0.06
     janvier
    -0.06
     SU
    -0.06
    .Pages
    -0.06
    -server
    -0.06
    ondheim
    -0.06
    POSITIVE LOGITS
    hesion
    0.08
    (car
    0.07
     fsm
    0.07
     ofrece
    0.07
     anyhow
    0.07
    631
    0.06
    Clearly
    0.06
    gs
    0.06
    ไทย
    0.06
     هل
    0.06
    Act Density 0.001%

    No Known Activations