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

    Neuronpedia

    INDEX
    Explanations

    numerical data and metrics

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

    numerical data values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <eos>
    -0.35
     
    -0.28
    …
    -0.27
    &&\
    -0.26
     verticales
    -0.26
    \
    -0.25
     Withers
    -0.24
     applied
    -0.24
     vertik
    -0.24
    </em>
    -0.23
    POSITIVE LOGITS
    [@BOS@]
    0.85
    <unused41>
    0.85
    <unused28>
    0.85
    <unused16>
    0.85
    <unused17>
    0.84
    <unused14>
    0.84
    <unused21>
    0.84
    <unused23>
    0.84
    <unused3>
    0.84
    <unused8>
    0.84
    Act Density 0.382%

    No Known Activations