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

    Neuronpedia

    INDEX
    Explanations

    programming functions and methods with specific parameters and return types

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

    creating code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Italij
    -0.46
    Atentamente
    -0.41
     laikā
    -0.41
     mandatario
    -0.40
     Preisen
    -0.40
     poitrine
    -0.39
     valentín
    -0.38
     oposición
    -0.38
     humanidad
    -0.38
     totalidad
    -0.38
    POSITIVE LOGITS
     Create
    0.86
     creation
    0.85
     created
    0.83
     Creating
    0.82
     create
    0.81
    Creating
    0.79
    Create
    0.79
    creation
    0.79
     Creation
    0.79
     createNew
    0.79
    Act Density 0.111%

    No Known Activations