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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ol
    -0.08
    程度
    -0.07
     order
    -0.07
    ).↵↵↵↵
    -0.07
    _COL
    -0.07
     sequencing
    -0.07
    ておく
    -0.07
    才干
    -0.07
    ities
    -0.07
     Unless
    -0.07
    POSITIVE LOGITS
     budd
    0.08
     initializes
    0.08
    教导
    0.08
     conectar
    0.07
     democrat
    0.07
     opponent
    0.07
    (fixture
    0.07
     deliberate
    0.07
     Fires
    0.07
     cultivating
    0.07
    Act Density 0.002%

    No Known Activations