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

    Neuronpedia

    INDEX
    Explanations

    patterns in structured data formats like arrays

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

    arrow assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Económica
    -0.43
     Italij
    -0.41
     fédé
    -0.41
    berdayakan
    -0.40
     femininas
    -0.40
     Estructura
    -0.40
     guerres
    -0.40
     Milán
    -0.39
     Redacción
    -0.39
     Capacidad
    -0.39
    POSITIVE LOGITS
     =>
    1.34
    =>
    0.92
     =>
    0.82
    Personendaten
    0.79
    SequentialGroup
    0.78
     ==>
    0.78
    =>"
    0.77
    =>$
    0.73
     =>'
    0.72
    =>'
    0.72
    Act Density 0.014%

    No Known Activations