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

    Neuronpedia

    INDEX
    Explanations

    places where articles are cut off, and links to continue or read the article

    oai_token-act-pair · gemini-2.0-flash

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.61
    GraphicsUnit
    -0.57
    soort
    -0.48
     kasarigan
    -0.47
    nessed
    -0.47
     الرياضيه
    -0.47
     Italijanski
    -0.45
    transQ
    -0.44
    dorff
    -0.44
     supers
    -0.44
    POSITIVE LOGITS
    ^(@)
    0.54
     Allociné
    0.53
     tartalomajánló
    0.51
    Personensuche
    0.50
     dignité
    0.48
    laq
    0.48
    
    0.47
    ⓧ
    0.46
    RetentionPolicy
    0.46
    ficult
    0.46
    Act Density 0.597%

    No Known Activations