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

    Neuronpedia

    INDEX
    Explanations

    numeric data and its associated formats

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

    Abbreviations followed by specific characters

    np_acts-logits-general · gemini-2.0-flash

    legal citations and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ch
    -1.38
     CH
    -1.31
    CH
    -1.29
    ch
    -1.29
    Ch
    -1.28
     Ch
    -1.26
    cha
    -1.15
     cha
    -1.14
     chi
    -1.13
     sh
    -1.12
    POSITIVE LOGITS
     Taz
    0.57
    pielen
    0.51
    pielt
    0.48
    Taz
    0.47
    mbggenerated
    0.44
    timmt
    0.43
    ργασ
    0.42
    pannt
    0.42
     الحره
    0.41
     AspNetCore
    0.40
    Act Density 1.125%

    No Known Activations