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

    Neuronpedia

    INDEX
    Explanations

    equals sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _mapping
    -0.07
     prefix
    -0.07
    สาย
    -0.06
    olang
    -0.06
    ipmap
    -0.06
     ци
    -0.06
     McCartney
    -0.06
     weapon
    -0.06
     pipeline
    -0.06
     vacuum
    -0.06
    POSITIVE LOGITS
    ้าอ
    0.06
     спе
    0.06
    tempts
    0.06
    _spi
    0.06
    ặt
    0.06
     unheard
    0.06
    にして
    0.06
    有什么
    0.06
    했
    0.06
    efficient
    0.06
    Act Density 0.006%

    No Known Activations