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

    Neuronpedia

    INDEX
    Explanations

    important terms related to technical functions and processes in various contexts

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

    awards and achievements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.94
    parsedMessage
    -0.88
     محفوظة
    -0.81
    الحياه
    -0.79
     برانيه
    -0.78
     surla
    -0.76
     betweenstory
    -0.71
    PerformLayout
    -0.71
     BoxFit
    -0.69
    :✨
    -0.68
    POSITIVE LOGITS
    ↵
    0.49
    ;
    0.47
     and
    0.44
     with
    0.43
     if
    0.41
     for
    0.41
    ↵↵
    0.41
    ,
    0.41
     (
    0.40
    .
    0.40
    Act Density 0.030%

    No Known Activations