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

    Neuronpedia

    INDEX
    Explanations

    technical writing introducing new technology and explaining how it works.

    oai_token-act-pair · gemini-2.0-flash

    scientific methodologies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.58
    WebElementEntity
    -0.57
    WithIOException
    -0.57
    sizeCache
    -0.55
    !")
    -0.55
    ?
    -0.54
    tanleria
    -0.52
     riuscito
    -0.52
    nodoc
    -0.50
    IntoConstraints
    -0.50
    POSITIVE LOGITS
     Roskov
    0.62
     beginnetje
    0.61
    ftagPool
    0.56
    Autoritní
    0.54
     autorytatywna
    0.52
    expandindo
    0.49
    Fordítás
    0.48
     '\\;'
    0.47
     scorso
    0.46
     metu
    0.45
    Act Density 6.690%

    No Known Activations