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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "do" in various forms and contexts

    oai_token-act-pair · gemini-2.0-flash

    verb "do" context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )}</
    -0.65
     nôtre
    -0.60
    DockStyle
    -0.57
    tonode
    -0.57
     leçon
    -0.57
    inot
    -0.57
     DbType
    -0.56
    enumii
    -0.56
     kaynağından
    -0.56
     pattes
    -0.55
    POSITIVE LOGITS
    Демографія
    0.56
    twimg
    0.52
    참고
    0.49
    Nada
    0.48
     nada
    0.48
     CURIAM
    0.45
    UnsafeEnabled
    0.44
     primul
    0.43
    gatsby
    0.43
     bazie
    0.42
    Act Density 4.104%

    No Known Activations