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

    Neuronpedia

    INDEX
    Explanations

    specialized terminology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kil
    0.73
    Sal
    0.72
    ăl
    0.70
     Sal
    0.69
     Gord
    0.68
     Grass
    0.68
    ங்குக
    0.67
     Stad
    0.67
     Joey
    0.66
    افة
    0.66
    POSITIVE LOGITS
    </h3>
    0.58
     despatch
    0.56
     ma
    0.56
     सौरभ
    0.56
     způ
    0.55
    ႄ
    0.55
     হবি
    0.55
     annonce
    0.55
     conteú
    0.54
     Nucleaires
    0.54
    Act Density 0.813%

    No Known Activations