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

    Neuronpedia

    INDEX
    Explanations

    code syntax and structure elements typically found in programming

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

    Code snippets with brackets and semicolons

    np_acts-logits-general · gemini-2.0-flash

    closing code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.68
     Saltar
    -0.62
     getItemId
    -0.56
    帖最后由
    -0.56
     kveld
    -0.55
    الدراسه
    -0.54
    Carriera
    -0.53
    НИК
    -0.51
    ::{
    -0.50
    InputTagHelper
    -0.50
    POSITIVE LOGITS
    <eos>
    3.05
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.81
    ↵↵↵↵↵↵↵↵
    0.76
    ↵↵↵↵↵↵↵
    0.75
    );*/
    0.75
    ↵↵↵↵↵↵↵↵↵
    0.75
    "}";
    0.75
    "]}
    0.74
    Portail
    0.74
    ↵↵↵↵↵↵↵↵↵↵↵
    0.73
    Act Density 0.366%

    No Known Activations