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

    Neuronpedia

    INDEX
    Explanations

    mentions of conversations

    oai_token-act-pair · gemini-2.0-flash

    conversation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    </i>
    -0.69
    .
    -0.65
    </b>
    -0.57
    ,
    -0.55
    </em>
    -0.55
    tvguidetime
    -0.55
    làm
    -0.54
     and
    -0.54
    </u>
    -0.53
     peix
    -0.51
    POSITIVE LOGITS
    <bos>
    1.00
     myſelf
    0.95
    InjectAttribute
    0.90
     pleaſure
    0.88
     purpoſe
    0.88
     ſmall
    0.82
    RectangleBorder
    0.82
     Monfieur
    0.80
    UnusedPrivate
    0.80
    AddTagHelper
    0.80
    Act Density 1.407%

    No Known Activations