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

    Neuronpedia

    INDEX
    Explanations

    java Spring Framework code

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     myſelf
    -0.69
     itſelf
    -0.65
     poffible
    -0.65
     purpoſe
    -0.63
     ſeveral
    -0.63
     themſelves
    -0.60
     reaſon
    -0.59
     Majefty
    -0.59
     himſelf
    -0.58
     poffe
    -0.58
    POSITIVE LOGITS
    <bos>
    1.02
     상세
    0.38
    tel
    0.38
    ola
    0.38
    mar
    0.38
    nod
    0.37
    gel
    0.36
    Paginator
    0.36
    lac
    0.36
    вей
    0.36
    Act Density 0.253%

    No Known Activations