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

    Neuronpedia

    INDEX
    Explanations

    respect and sensitive communication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     activation
    0.92
     Activation
    0.89
     optimizer
    0.86
    activation
    0.86
     Configuration
    0.86
     activates
    0.79
     activations
    0.79
     launcher
    0.79
     Configuring
    0.78
     gefähr
    0.78
    POSITIVE LOGITS
     respectful
    3.11
     respect
    2.56
    Respect
    2.56
     Respect
    2.53
     respeto
    2.50
    尊重
    2.44
     respecting
    2.37
    respect
    2.30
     respects
    2.16
     respectfully
    2.12
    Act Density 0.559%

    No Known Activations