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

    Neuronpedia

    INDEX
    Explanations

    specific names and identifiers in a technical or formal context

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

    mathematical and technical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TRIBUN
    -0.36
    iren
    -0.36
    #!/
    -0.35
     Verfügung
    -0.33
    cerna
    -0.32
     الر
    -0.32
    Jake
    -0.32
     Jake
    -0.31
    """
    -0.31
    xhr
    -0.30
    POSITIVE LOGITS
     betweenstory
    0.77
    principalColumn
    0.75
     propOrder
    0.72
     GenerationType
    0.70
     lenker
    0.68
    posedge
    0.65
    SharedDtor
    0.62
    UserScript
    0.60
     '\\;'
    0.59
    Lähteet
    0.59
    Act Density 0.602%

    No Known Activations