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

    Neuronpedia

    INDEX
    Explanations

    the start of new sections of text

    oai_token-act-pair · gemini-2.0-flash

    Technical/academic document excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    contentLoaded
    -0.52
    ilan
    -0.50
    ://$
    -0.48
    pas
    -0.46
    <bos>
    -0.46
    AutoScaleMode
    -0.44
     Walkover
    -0.43
     <>",
    -0.43
     naman
    -0.43
    rena
    -0.43
    POSITIVE LOGITS
     myſelf
    0.54
     Theſe
    0.52
     Monfieur
    0.52
    RUnlock
    0.50
    uttavia
    0.48
    tanleria
    0.48
     Cæsar
    0.47
    клопе
    0.47
     Jefus
    0.46
     becauſe
    0.46
    Act Density 0.632%

    No Known Activations