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

    Neuronpedia

    INDEX
    Explanations

    C code, especially code using the Nginx web server framework

    oai_token-act-pair · gemini-2.0-flash

    unusual or uncommon tokens

    np_token-act-pair-logits · gpt-4o-mini

    _

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    出版年
    -0.67
     the
    -0.55
    ],\
    -0.51
     And
    -0.50
    azas
    -0.50
    seks
    -0.50
     sebanyak
    -0.49
    <bos>
    -0.49
     Browne
    -0.49
     non
    -0.48
    POSITIVE LOGITS
     kasarigan
    0.77
     ་་
    0.76
     Monfieur
    0.73
    numerusform
    0.73
    ThroughAttribute
    0.72
     doubtnut
    0.71
     gawas
    0.70
    UrlResolution
    0.70
     pleaſure
    0.70
    itinéraire
    0.69
    Act Density 5.405%

    No Known Activations