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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     skill
    0.78
     skills
    0.75
    Skill
    0.69
     Skill
    0.62
    skill
    0.62
     сп
    0.61
     కల
    0.61
    ஷம்
    0.60
     blow
    0.60
     verbal
    0.60
    POSITIVE LOGITS
     Anwendungen
    1.06
     contexts
    1.05
     environments
    1.03
     applicazioni
    0.97
     deployments
    0.97
    乃至
    0.97
    における
    0.95
     ambienti
    0.95
    에서도
    0.94
    中使用
    0.93
    Act Density 4.261%

    No Known Activations