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

    Neuronpedia

    INDEX
    Explanations

    monetary values or dollar amounts

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

    percentages and numerical values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    I
    -0.39
    E
    -0.36
    i
    -0.34
    ↵
    -0.33
      
    -0.33
    G
    -0.32
    N
    -0.31
    W
    -0.31
    B
    -0.31
    g
    -0.31
    POSITIVE LOGITS
    <unused3>
    1.28
    <unused74>
    1.28
    <unused52>
    1.28
    <unused68>
    1.28
    <unused8>
    1.28
    [@BOS@]
    1.28
    <unused41>
    1.28
    <unused23>
    1.27
    <unused16>
    1.27
    <unused14>
    1.27
    Act Density 0.004%

    No Known Activations