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

    Neuronpedia

    INDEX
    Explanations

    attribute name="="

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oretically
    1.40
    র
    1.22
    ৬
    1.16
     가능하다
    1.13
    _
    1.10
    $,
    1.08
    l
    1.08
    $.
    1.04
    ﻥ
    1.02
    ﺱ
    1.02
    POSITIVE LOGITS
    될
    1.20
    ﻰ
    1.17
     axonal
    1.15
     vẻ
    1.09
    ga
    1.09
    ба
    1.09
     Anfang
    1.09
    Charsets
    1.07
    Ин
    1.06
    Ле
    1.06
    Act Density 0.015%

    No Known Activations