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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical data or configurations in technical contexts

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

    zero or nil

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.90
     betweenstory
    -0.88
    transQ
    -0.88
    <unused28>
    -0.86
    <unused79>
    -0.85
    [@BOS@]
    -0.85
    <unused8>
    -0.85
    <unused11>
    -0.85
    <unused3>
    -0.85
    <pad>
    -0.85
    POSITIVE LOGITS
    0
    0.68
     zero
    0.68
     Zero
    0.52
    Zero
    0.47
    zero
    0.46
     cero
    0.45
     ZERO
    0.39
    ZERO
    0.39
     zéro
    0.37
     nil
    0.32
    Act Density 0.046%

    No Known Activations