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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a document or section

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

    Text following possible delimiters

    np_acts-logits-general · gemini-2.0-flash

    PBS blocking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.79
     الحره
    -0.78
    numerusform
    -0.75
    RegressionTest
    -0.75
     resourceCulture
    -0.66
    DeleteBehavior
    -0.66
     تضيفلها
    -0.66
     \%$\\
    -0.64
    
    -0.63
    FunctionFlags
    -0.63
    POSITIVE LOGITS
    <bos>
    0.73
     honra
    0.53
    lotl
    0.53
    RRect
    0.52
     femininas
    0.49
    L
    0.48
     saia
    0.48
    VIATIONS
    0.48
    J
    0.45
     aldus
    0.44
    Act Density 0.078%

    No Known Activations