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

    Neuronpedia

    INDEX
    Explanations

    structured data fields or tags typically used in programming or markup languages

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

    code structure with assignments and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.90
     defaultstate
    -0.90
     Infórmanos
    -0.88
     indígen
    -0.84
     незавершена
    -0.82
     autorytatywna
    -0.82
    fromnode
    -0.79
    parsedMessage
    -0.78
     queſta
    -0.75
     snippetHide
    -0.75
    POSITIVE LOGITS
     
    0.58
     the
    0.53
    The
    0.48
    .
    0.47
     A
    0.47
     (
    0.46
     The
    0.43
     S
    0.41
    ,
    0.41
    2
    0.40
    Act Density 0.023%

    No Known Activations