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

    Neuronpedia

    INDEX
    Explanations

    pain and suffering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    loops
    0.39
    Loops
    0.39
    㷌
    0.39
    ෙන
    0.38
     reassurance
    0.38
    ූප
    0.37
    ieza
    0.37
    ネジ
    0.37
    گر
    0.36
    weathermap
    0.36
    POSITIVE LOGITS
     painful
    0.78
     dec
    0.70
     doulou
    0.58
     Pain
    0.58
    痛
    0.58
    pain
    0.57
     đau
    0.57
    Pain
    0.55
     painfully
    0.55
     dolor
    0.54
    Act Density 0.000%

    No Known Activations