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

    Neuronpedia

    INDEX
    Explanations

    past hardships and suffering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aiz
    0.66
     curioso
    0.65
    Homemade
    0.62
    surprisingly
    0.62
     sneaky
    0.61
    nosť
    0.61
     konu
    0.60
    Surprisingly
    0.60
     éton
    0.59
     veloce
    0.59
    POSITIVE LOGITS
     hardships
    2.60
     hardship
    2.58
     misery
    2.56
     sufferings
    2.55
     suffering
    2.52
     anguish
    2.27
     oppression
    2.22
     trauma
    2.18
     pain
    2.18
     adversity
    2.14
    Act Density 0.887%

    No Known Activations