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

    Neuronpedia

    INDEX
    Explanations

    expressing sadness or sympathy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Much
    0.49
     Sending
    0.47
     Trag
    0.45
     விலை
    0.45
     Deep
    0.45
     sending
    0.44
     Sad
    0.44
    लेस
    0.42
    Sending
    0.42
     So
    0.41
    POSITIVE LOGITS
     stunned
    0.45
     agnostic
    0.43
     atheist
    0.42
    CrL
    0.40
     landsc
    0.39
     shocked
    0.39
    震惊
    0.39
     cStart
    0.38
    sorption
    0.38
     knit
    0.38
    Act Density 0.001%

    No Known Activations