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

    Neuronpedia

    INDEX
    Explanations

    AI Chatbot and language model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    好友
    0.66
     agents
    0.62
     agent
    0.59
    ylie
    0.59
    ozer
    0.58
    MAS
    0.58
     Agent
    0.57
    Mark
    0.56
    चुरी
    0.56
     Eliot
    0.55
    POSITIVE LOGITS
     തെ
    0.65
     Tight
    0.63
    δε
    0.63
    ▴
    0.62
     tighten
    0.62
     prehr
    0.61
    Capabilities
    0.61
     टेक
    0.60
    olées
    0.60
    credential
    0.60
    Act Density 0.172%

    No Known Activations