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

    Neuronpedia

    INDEX
    Explanations

    return ( JSX code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    נק
    0.41
     adquis
    0.40
    кова
    0.39
     fonctions
    0.39
     hätten
    0.39
    ஞ்சு
    0.39
    쾨
    0.39
     determ
    0.39
     تھی۔
    0.39
     கட்டுமான
    0.38
    POSITIVE LOGITS
     (<
    0.80
    <div>
    0.75
     <
    0.74
    (<
    0.68
     <>
    0.66
    =<
    0.65
     `<
    0.63
    <>
    0.63
     [<
    0.60
    }<
    0.59
    Act Density 0.002%

    No Known Activations