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

    Neuronpedia

    INDEX
    Explanations

    account registration requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Autonomous
    0.40
     generality
    0.39
     cuidado
    0.38
     Whoever
    0.38
     cuidad
    0.38
    Consumers
    0.37
    Wireless
    0.37
    parallel
    0.37
     Consumers
    0.37
     Automated
    0.36
    POSITIVE LOGITS
     registration
    0.84
     signup
    0.75
    Registration
    0.73
     Registration
    0.72
    registration
    0.70
     регистрации
    0.69
     реєстра
    0.69
    注册
    0.63
     Signup
    0.62
     регистра
    0.61
    Act Density 0.018%

    No Known Activations