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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

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

    "in this" sentence structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IUrlHelper
    -0.70
    Portale
    -0.69
    endphp
    -0.69
    SBATCH
    -0.68
    ImageContext
    -0.67
    istoitu
    -0.66
    LEncoder
    -0.65
    RTDA
    -0.63
    <bos>
    -0.60
    RegressionTest
    -0.60
    POSITIVE LOGITS
     nosotros
    0.37
     Wolken
    0.36
     we
    0.35
     you
    0.35
    läs
    0.35
    [,
    0.34
    kmäler
    0.34
    ivin
    0.34
     banque
    0.34
    UNDO
    0.33
    Act Density 0.032%

    No Known Activations