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

    Neuronpedia

    INDEX
    Explanations

    fictional entities and reusable technology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     může
    0.43
     dítě
    0.43
     اچھی
    0.43
    によっては
    0.43
    šku
    0.42
    indicating
    0.42
     considérons
    0.41
     heinous
    0.41
     indiquant
    0.41
     frecuentes
    0.40
    POSITIVE LOGITS
     parchment
    0.62
    生产
    0.47
     holographic
    0.47
     contracts
    0.46
     design
    0.45
     guilds
    0.44
     modal
    0.43
     polycarbonate
    0.43
    集成
    0.43
    上传
    0.42
    Act Density 0.003%

    No Known Activations