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

    Neuronpedia

    INDEX
    Explanations

    function

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    際
    -0.06
     sex
    -0.06
     moderate
    -0.06
     witness
    -0.06
     Month
    -0.06
    Aspect
    -0.06
    방송
    -0.06
     الث
    -0.06
     tempered
    -0.06
     decay
    -0.06
    POSITIVE LOGITS
    ";//
    0.08
    /documentation
    0.07
    anked
    0.07
    .tagName
    0.07
     extravag
    0.07
     людина
    0.07
    achusetts
    0.06
     geliş
    0.06
    .dependencies
    0.06
    атем
    0.06
    Act Density 0.005%

    No Known Activations