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
     mildly
    0.51
     उत्सा
    0.49
     relax
    0.48
     उत्सुक
    0.48
     giggle
    0.46
     উদ্দীপ
    0.46
     relaxation
    0.46
     gemüt
    0.45
     உற்ச
    0.45
     उत्साह
    0.45
    POSITIVE LOGITS
     pain
    1.76
     hurt
    1.63
     painful
    1.63
    pain
    1.55
    Pain
    1.54
     Pain
    1.53
     hurts
    1.49
     heartbreak
    1.46
     heartache
    1.45
     pijn
    1.44
    Act Density 0.096%

    No Known Activations