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

    Neuronpedia

    INDEX
    Explanations

    colons and their associated structures

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

    Punctuation, especially colons

    np_acts-logits-general · gemini-2.0-flash

    code examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.90
    脚注の使い方
    -0.71
     continúas
    -0.61
    ngrx
    -0.60
     Савезне
    -0.59
    <bos>
    -0.59
     Приступљено
    -0.58
     мәкалә
    -0.58
    ORAGE
    -0.56
    NSNotification
    -0.56
    POSITIVE LOGITS
    ↵↵
    1.34
    <eos>
    1.09
    ↵↵↵
    1.08
    ↵↵↵↵
    0.98
    ↵
    0.91
    ↵↵↵↵↵
    0.89
    ↵↵↵↵↵↵↵
    0.83
    ↵↵↵↵↵↵
    0.81
    ↵↵↵↵↵↵↵↵↵
    0.76
    ↵↵↵↵↵↵↵↵↵↵↵
    0.75
    Act Density 0.232%

    No Known Activations