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

    Neuronpedia

    INDEX
    Explanations

    test

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Around
    -0.07
     around
    -0.07
    arrow
    -0.06
     Arrow
    -0.06
     برخورد
    -0.06
    که
    -0.06
    630
    -0.06
    ovíd
    -0.06
    [char
    -0.06
    ARCHAR
    -0.06
    POSITIVE LOGITS
     test
    0.14
     tests
    0.12
     Test
    0.12
    Test
    0.11
    .test
    0.10
    test
    0.10
    _test
    0.09
     Tests
    0.09
    TEST
    0.09
    -test
    0.09
    Act Density 0.070%

    No Known Activations