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

    Neuronpedia

    INDEX
    Explanations

    java imports and semicolons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    addena
    0.39
    cevam
    0.36
     एक्सरसा
    0.36
    𒇽
    0.35
    <unused40>
    0.34
    lovepoetry
    0.34
     शौचालय
    0.34
    माइंडर
    0.33
    ুতরাং
    0.33
    मस्कार
    0.32
    POSITIVE LOGITS
    ,
    0.45
    ;
    0.44
    <0x0D>
    0.43
    -
    0.43
    ，
    0.41
    、
    0.39
    .
    0.39
    ↵↵
    0.38
     from
    0.38
     and
    0.38
    Act Density 0.035%

    No Known Activations