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

    Neuronpedia

    INDEX
    Explanations

    ```. elab >```

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    द
    0.52
     welcoming
    0.48
    രിച്ചത്
    0.44
    তাদের
    0.42
    颢
    0.42
    Есть
    0.42
    وی
    0.41
     средств
    0.41
     konserv
    0.40
     contempt
    0.39
    POSITIVE LOGITS
     manzanas
    0.49
    मर्रा
    0.49
    brahim
    0.48
    ácter
    0.47
    两种
    0.46
     oración
    0.46
    uigen
    0.46
     mantras
    0.46
    ಿಕ್
    0.45
    ':[
    0.45
    Act Density 0.001%

    No Known Activations