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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    These
    -0.07
    ody
    -0.07
     weekend
    -0.07
    ตน
    -0.06
     finally
    -0.06
    nero
    -0.06
    -*
    -0.06
    وجود
    -0.06
     Hassan
    -0.06
     These
    -0.06
    POSITIVE LOGITS
    .opengl
    0.07
    ":""
    0.07
    (Tag
    0.07
     landslide
    0.07
    πος
    0.07
     EXTRA
    0.06
    _SESSION
    0.06
    Prompt
    0.06
     залиш
    0.06
     lcm
    0.06
    Act Density 0.001%

    No Known Activations