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

    Neuronpedia

    INDEX
    Explanations

    stirring something within or awakening

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     for
    1.48
     The
    1.20
     (
    1.17
     de
    1.17
    /
    1.13
    ede
    1.11
     p
    1.08
    :
    1.08
    illy
    1.05
    ari
    1.02
    POSITIVE LOGITS
    ために
    1.22
    ્સ
    1.22
     članak
    1.20
     stirs
    1.19
     взя
    1.18
    ため
    1.16
     powied
    1.15
    ுகள்
    1.14
     Фурга
    1.14
    σε
    1.13
    Act Density 0.004%

    No Known Activations