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

    Neuronpedia

    INDEX
    Explanations

    instances of whitespace or indentation in the text

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

    code and documentation comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    flashdata
    -0.55
    ="@+
    -0.48
     arşivlendi
    -0.48
    copg
    -0.44
    LEncoder
    -0.43
     Normdatei
    -0.43
    errHandler
    -0.42
    また
    -0.41
    :✨
    -0.41
    iedenis
    -0.40
    POSITIVE LOGITS
    .*")]
    0.53
    +#+
    0.53
     informée
    0.50
     detailsLots
    0.48
    sprung
    0.46
    transQ
    0.46
    }*/
    0.46
     Root
    0.45
    */;
    0.45
     Trans
    0.44
    Act Density 0.020%

    No Known Activations