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

    Neuronpedia

    INDEX
    Explanations

    coding syntax related to function returns and structured data formats

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

    error messages and responses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.71
    DockStyle
    -0.68
     تضيفلها
    -0.61
    MigrationBuilder
    -0.57
     informée
    -0.54
    abstractmethod
    -0.49
    تقاوى
    -0.47
     normalidad
    -0.46
     Normdatei
    -0.46
    BagLayout
    -0.45
    POSITIVE LOGITS
     jsonify
    0.43
     error
    0.41
    :].
    0.41
     Flamingo
    0.39
     scal
    0.38
     invalid
    0.38
     return
    0.38
     fur
    0.38
     suspension
    0.38
     gun
    0.37
    Act Density 0.001%

    No Known Activations