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

    Neuronpedia

    INDEX
    Explanations

    punctuations and delimiters in the text

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

    Characters following a backslash or period

    np_acts-logits-general · gemini-2.0-flash

    math and code symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StoryboardSegue
    -0.67
     contextLoads
    -0.63
     ſtate
    -0.63
    듦
    -0.63
     testSet
    -0.62
     houſe
    -0.61
    Przypisy
    -0.59
    ">:
    -0.56
     للاسماء
    -0.55
     Shakspeare
    -0.55
    POSITIVE LOGITS
    <bos>
    0.79
    expandindo
    0.68
    Autoritní
    0.65
    UserScript
    0.58
    abestanden
    0.54
    PerformLayout
    0.54
    ViewFeatures
    0.52
    ganu
    0.51
    ecma
    0.51
    ں
    0.51
    Act Density 0.285%

    No Known Activations