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

    Neuronpedia

    INDEX
    Explanations

    programming syntax elements and operations related to data handling

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

    <start_of_turn>user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pyplot
    -0.45
    thâu
    -0.45
    Bibliograf
    -0.44
    pyplot
    -0.43
     betweenstory
    -0.43
     BoxFit
    -0.43
    enumi
    -0.43
    wpi
    -0.43
    httphttps
    -0.42
    usercontent
    -0.42
    POSITIVE LOGITS
    Args
    0.65
    args
    0.63
     Args
    0.54
     args
    0.54
    Params
    0.44
    ligare
    0.43
    sales
    0.43
    faults
    0.42
    shortest
    0.42
    decimal
    0.41
    Act Density 0.006%

    No Known Activations