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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers and associated notation

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

    technical terms like [\cite{...}]{ref-type}

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AntiForgeryToken
    -0.40
    e
    -0.37
    able
    -0.37
    ages
    -0.36
    due
    -0.36
    ed
    -0.35
     Baumann
    -0.35
     साम
    -0.35
    be
    -0.34
    use
    -0.34
    POSITIVE LOGITS
     betweenstory
    0.87
     Administrativna
    0.69
     surla
    0.67
     CreateTagHelper
    0.66
     Infórmanos
    0.64
     wireType
    0.60
    TokenNameDOT
    0.58
     oprot
    0.57
    الدراسه
    0.56
    iſchen
    0.56
    Act Density 0.001%

    No Known Activations