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

    Neuronpedia

    INDEX
    Explanations

    emotional reactions and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ặp
    0.95
     controversial
    0.81
     contentious
    0.78
     scary
    0.75
    irstyle
    0.75
     intimidating
    0.72
    افه
    0.72
     erred
    0.71
     Scary
    0.70
     memungkinkan
    0.70
    POSITIVE LOGITS
    ingly
    1.08
    不已
    0.99
     watching
    0.98
    스러운
    0.93
    Watching
    0.92
    Knowing
    0.89
     Watching
    0.89
     speechless
    0.89
     knowing
    0.88
     thoughts
    0.88
    Act Density 0.294%

    No Known Activations