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

    Neuronpedia

    INDEX
    Explanations

    copyright-related terms and phrases

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

    "Too" followed by a punctuation mark

    np_acts-logits-general · gemini-2.0-flash

    also, too, either, though

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    localctx
    -0.54
     ब्रेकडाउन
    -0.52
    Diweddarwch
    -0.51
    ValueGenerated
    -0.46
    下载附件
    -0.46
     nakalista
    -0.44
    asteroide
    -0.43
     MainAxisSize
    -0.42
    曖昧さ回避
    -0.40
    RegressionTest
    -0.40
    POSITIVE LOGITS
    TokenNameCOMMA
    0.53
    ValueStyle
    0.49
    ,..
    0.46
     שוליים
    0.45
    GOTREF
    0.45
    awtextra
    0.45
    ,:
    0.45
    ,.
    0.42
    ,-
    0.41
    ,…
    0.41
    Act Density 1.492%

    No Known Activations