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

    Neuronpedia

    INDEX
    Explanations

    type and following tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    =-
    0.84
    Jar
    0.78
    --“
    0.76
    ={(
    0.76
    ...”
    0.74
    ierry
    0.73
    beitung
    0.73
    _{*}$
    0.73
    ஞர்
    0.73
    Eva
    0.71
    POSITIVE LOGITS
    declar
    0.71
    dick
    0.69
    奢
    0.66
    )?;
    0.64
    ပါ
    0.64
    సర
    0.63
     channels
    0.62
    เมตร
    0.62
    ↵↵↵↵↵↵↵↵↵↵↵↵
    0.61
    ாடு
    0.61
    Act Density 0.002%

    No Known Activations