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

    Neuronpedia

    INDEX
    Explanations

    difficulty and hardship

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     C
    1.05
    ik
    1.00
    š
    0.96
    …………………………………………
    0.93
     U
    0.92
    0.90
    一遍
    0.89
    end
    0.84
     "
    0.84
    age
    0.84
    POSITIVE LOGITS
    栦
    1.16
    ھے
    1.08
    Д
    1.08
    Л
    1.08
     adversity
    1.06
    ISATION
    1.06
    prue
    1.06
    艰难
    1.04
     hardships
    1.02
     hardship
    1.01
    Act Density 0.185%

    No Known Activations