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

    Neuronpedia

    INDEX
    Explanations

    words with high sentiment polarity that are related to positive reviews or recommendations, and applies a boost to contexts where it is addressing the person being reviewed directly.

    oai_token-act-pair · gemini-2.0-flash

    re

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eapp
    -0.49
     bra
    -0.47
    وجد
    -0.47
     Gram
    -0.45
    نه
    -0.44
    boy
    -0.44
    clar
    -0.44
     nhà
    -0.43
     li
    -0.43
    bra
    -0.43
    POSITIVE LOGITS
    ValueStyle
    0.87
     Wikimedijinoj
    0.81
    styleType
    0.77
     незавершена
    0.73
     ErrIntOverflow
    0.70
    ViewFeatures
    0.70
    thâu
    0.69
    ScopeManager
    0.68
     "..\..\..\
    0.68
    TintMode
    0.67
    Act Density 0.388%

    No Known Activations