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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    orem
    -0.07
     Availability
    -0.06
    ography
    -0.06
     równ
    -0.06
    swer
    -0.06
    ber
    -0.06
    ophon
    -0.06
    Major
    -0.06
     floats
    -0.06
    ephy
    -0.06
    POSITIVE LOGITS
    _REQUIRE
    0.07
    =${
    0.07
    =c
    0.07
     malign
    0.07
    unun
    0.07
    stellar
    0.07
    (SELECT
    0.07
    )，
    0.07
    =j
    0.06
    .callbacks
    0.06
    Act Density 0.021%

    No Known Activations