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

    Neuronpedia

    INDEX
    Explanations

    confectionary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    મ
    1.38
    ло
    1.22
    К
    1.19
    ש
    1.19
    ور
    1.15
    with
    1.09
    रा
    1.08
    pesar
    1.05
    मा
    1.04
    ட
    1.04
    POSITIVE LOGITS
    <h4>
    1.19
     of
    1.12
    ’
    1.09
    ee
    1.08
    <h3>
    1.05
    era
    0.96
    는데
    0.91
    都
    0.90
    <h2>
    0.89
     Affleck
    0.89
    Act Density 0.000%

    No Known Activations