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

    Neuronpedia

    INDEX
    Explanations

    ure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hait
    -0.07
     گونه
    -0.07
     없었다
    -0.06
    RDD
    -0.06
    liğinde
    -0.06
     школ
    -0.06
    fclose
    -0.06
     elapsed
    -0.06
    検
    -0.06
    slaught
    -0.06
    POSITIVE LOGITS
    Local
    0.07
     Cache
    0.07
    /Input
    0.07
    _source
    0.06
    ature
    0.06
    IO
    0.06
    Communic
    0.06
     Offer
    0.06
    attles
    0.06
     institutions
    0.06
    Act Density 0.000%

    No Known Activations