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

    Neuronpedia

    INDEX
    Explanations

    numerical statistics or data points related to percentages

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

    percentages greater than 80

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    

    -0.35
    Meanwhile
    -0.28
    <strong>
    -0.27
     meanwhile
    -0.27
    　　
    -0.26
    ↵
    -0.26
    В
    -0.25
    
    -0.25
     Meanwhile
    -0.24
     

    -0.24
    POSITIVE LOGITS
     المعيارى
    1.09
    <unused68>
    0.96
    <unused8>
    0.96
    [@BOS@]
    0.95
    <unused52>
    0.95
    <unused32>
    0.95
    <unused43>
    0.95
    <unused42>
    0.95
    <unused14>
    0.95
    <unused28>
    0.95
    Act Density 0.057%

    No Known Activations