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

    Neuronpedia

    INDEX
    Explanations

    bleakness and despair

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    神奇
    0.41
     ServicePolicy
    0.41
    崧
    0.39
    啵
    0.39
    好奇
    0.39
    argate
    0.39
     برق
    0.39
     exciting
    0.39
     Dynamic
    0.38
     (+)
    0.38
    POSITIVE LOGITS
     despair
    2.25
     depressing
    2.23
     gloomy
    2.17
     gloom
    2.17
     hopelessness
    2.14
     pessimism
    2.14
     bleak
    2.11
     pessimistic
    2.05
     depressed
    2.02
     melancholy
    1.95
    Act Density 0.172%

    No Known Activations