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

    Neuronpedia

    INDEX
    Explanations

    cur

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    欄
    -0.07
    考研
    -0.07
    .exam
    -0.07
     Against
    -0.07
     lush
    -0.07
     resembling
    -0.07
    [Test
    -0.07
     FETCH
    -0.06
     Email
    -0.06
    peng
    -0.06
    POSITIVE LOGITS
    onne
    0.07
    โคร
    0.07
     Carroll
    0.07
    Clearly
    0.07
     Brewer
    0.07
    Connell
    0.06
     Wolver
    0.06
    ────
    0.06
    蟛
    0.06
     Chavez
    0.06
    Act Density 0.000%

    No Known Activations