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

    Neuronpedia

    INDEX
    Explanations

    specific programming constructs and functions

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

    Ends statements, lines, or sentences

    np_acts-logits-general · gemini-2.0-flash

    code and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.73
     ModelExpression
    -0.70
    MessageTagHelper
    -0.65
    LabelTagHelper
    -0.64
    BeginContext
    -0.63
     Infórmanos
    -0.60
     الرياضيه
    -0.59
    fromCharCode
    -0.59
    endphp
    -0.58
    WriteTagHelper
    -0.57
    POSITIVE LOGITS
    伝
    0.36
    rzez
    0.34
    hline
    0.34
    heads
    0.32
     ouvriers
    0.31
    傳
    0.31
    传
    0.31
     tráng
    0.31
     eğer
    0.31
     habido
    0.31
    Act Density 0.040%

    No Known Activations