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

    Neuronpedia

    INDEX
    Explanations

    foreign characters and code punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ()=>
    1.07
    出来る
    0.99
    出来ます
    0.99
     میتوان
    0.98
     ज़
    0.95
    ={()=>
    0.95
     occured
    0.94
     जरुर
    0.94
     Certainly
    0.94
     ()=>{
    0.93
    POSITIVE LOGITS
    ôle
    0.80
    ङ्
    0.75
    SDAY
    0.74
     घड़ी
    0.72
    Ş
    0.71
    vý
    0.70
     rač
    0.70
     počíta
    0.70
     സ്‌
    0.70
    .—
    0.70
    Act Density 0.277%

    No Known Activations