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

    Neuronpedia

    INDEX
    Explanations

    foreign language tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     】
    0.66
     ・
    0.64
     homomorphism
    0.64
     』
    0.64
     ́
    0.63
     $=$
    0.63
     ء
    0.61
     \*
    0.60
     ');
    0.60
     $$\
    0.60
    POSITIVE LOGITS
    <unused940>
    0.82
    <unused1200>
    0.75
    ர்களும்
    0.68
    Những
    0.68
    <unused1658>
    0.67
    тім
    0.66
    <unused1786>
    0.66
    <unused1011>
    0.65
    𒉺
    0.65
    Após
    0.64
    Act Density 0.166%

    No Known Activations