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

    Neuronpedia

    INDEX
    Explanations

    percentages and numerical data within URLs or references

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

    number followed by special characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    -0.40
    ↵↵↵
    -0.37
    ↵↵
    -0.35
     and
    -0.34
    /
    -0.34
     which
    -0.33
     (
    -0.32
    ，
    -0.32
        
    -0.31
     &
    -0.31
    POSITIVE LOGITS
    <unused41>
    0.98
    <unused14>
    0.98
    <unused3>
    0.98
    <unused8>
    0.98
    <unused68>
    0.98
    <unused79>
    0.98
    <unused28>
    0.98
    <unused23>
    0.98
    <unused16>
    0.98
    <unused17>
    0.98
    Act Density 0.039%

    No Known Activations