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

    Neuronpedia

    INDEX
    Explanations

    occurrences of conversational text along with discourse markers, like filled pauses

    oai_token-act-pair · gemini-2.0-flash

    See

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WithIOException
    -0.69
     invokingState
    -0.67
    SequentialGroup
    -0.66
     calendriers
    -0.63
    IUrlHelper
    -0.61
     AspNetCore
    -0.60
     Exacts
    -0.60
    newswire
    -0.60
    awtextra
    -0.60
    PreferredItem
    -0.58
    POSITIVE LOGITS
     see
    2.30
     See
    1.95
    see
    1.94
    See
    1.90
     SEE
    1.63
     sees
    1.56
    SEE
    1.52
     seeing
    1.26
     siehe
    1.22
     voir
    1.20
    Act Density 0.788%

    No Known Activations