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

    Neuronpedia

    INDEX
    Explanations

    computer configuration settings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     transformative
    -0.07
     Wit
    -0.07
     ورود
    -0.07
    печ
    -0.07
     مذ
    -0.06
    Compression
    -0.06
     NoSuch
    -0.06
    citation
    -0.06
     bumper
    -0.06
     borne
    -0.06
    POSITIVE LOGITS
    圣
    0.08
    igo
    0.07
     Eastern
    0.07
     belirli
    0.07
     중
    0.06
    ulia
    0.06
     cost
    0.06
    že
    0.06
    亚
    0.06
    :normal
    0.06
    Act Density 0.037%

    No Known Activations