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

    Neuronpedia

    INDEX
    Explanations

    specific word followed by another word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    1.99
    <0x0D>
    0.87
    $\
    0.64
    ↵↵
    0.64
    Ко
    0.62
    
    0.61
    .
    0.60
    На
    0.58
    $
    0.57
    timeline
    0.57
    POSITIVE LOGITS
    <eos>
    1.00
     […]
    0.82
     [...]
    0.69
     阅读全文
    0.65
    ៕
    0.63
     "));
    0.62
     “…
    0.61
    /"><
    0.60
    "},{"
    0.60
     ["[
    0.59
    Act Density 0.000%

    No Known Activations