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

    Neuronpedia

    INDEX
    Explanations

    dollar signs and related monetary symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets or questions

    np_acts-logits-general · gemini-2.0-flash

    programming examples and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ^(@)
    -0.89
    vantages
    -0.76
     uſed
    -0.75
    @@@@@@@@
    -0.75
    ſelves
    -0.75
     (\%
    -0.74
     doubtnut
    -0.73
     Houſe
    -0.73
    MLLoader
    -0.73
    leſs
    -0.73
    POSITIVE LOGITS
    </em>
    1.08
    </i>
    0.88
    <em>
    0.87
    <i>
    0.69
    r
    0.68
    <u>
    0.67
    i
    0.67
    <strong>
    0.63
    ing
    0.60
    findpost
    0.59
    Act Density 0.206%

    No Known Activations