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

    Neuronpedia

    INDEX
    Explanations

    col, coup, cole words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     avanzados
    0.38
     முன்னணி
    0.36
    सेट
    0.35
     میز
    0.35
    nać
    0.34
    wikk
    0.34
     communs
    0.34
     වඩා
    0.34
     చేసుకోవ
    0.34
    odom
    0.33
    POSITIVE LOGITS
     footing
    0.39
    驍
    0.39
     Lew
    0.38
    Lew
    0.38
     identification
    0.38
    த்தைக்
    0.37
     लार
    0.37
    តម្លៃ
    0.37
     హైదర్
    0.36
    ATED
    0.35
    Act Density 0.002%

    No Known Activations