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

    Neuronpedia

    INDEX
    Explanations

    success, focus, changes, rice, dramatic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    y
    1.63
    at
    1.56
    ly
    1.24
    ar
    1.15
    д
    1.14
     Whilst
    1.13
    Whilst
    1.09
    ⣀
    1.07
    yyyy
    1.06
     mighty
    1.03
    POSITIVE LOGITS
    nosed
    1.33
    У
    1.31
    <unused100>
    1.26
    அ
    1.24
    количество
    1.21
    ignées
    1.20
    ্যালেঞ্জ
    1.16
     inwon
    1.16
    getSaveLocation
    1.14
     tenham
    1.14
    Act Density 0.000%

    No Known Activations