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

    Neuronpedia

    INDEX
    Explanations

    structural elements and definitions in programming code

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

    module or Trait

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reciclaje
    -0.60
     motocicleta
    -0.57
    principalColumn
    -0.54
     nutrición
    -0.54
     volcán
    -0.53
    ksikon
    -0.52
     granja
    -0.52
     arcilla
    -0.52
    etheless
    -0.52
     cirugía
    -0.52
    POSITIVE LOGITS
     exists
    0.40
    ActiveRecord
    0.35
    finger
    0.35
    migo
    0.35
     exist
    0.35
    rosen
    0.35
    ishna
    0.35
    Sy
    0.35
    thum
    0.34
     Origen
    0.34
    Act Density 0.004%

    No Known Activations