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

    Neuronpedia

    INDEX
    Explanations

    sadness melancholy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    紧张
    0.48
    緊張
    0.48
    apanam
    0.47
     वैद्य
    0.46
     Crisis
    0.42
     shocks
    0.41
     Positive
    0.41
     terrified
    0.41
     दिव्य
    0.41
     Bolts
    0.40
    POSITIVE LOGITS
     triste
    0.71
     sad
    0.70
     lament
    0.68
     melancholy
    0.62
     lamented
    0.59
    sad
    0.59
     buồn
    0.59
     Lament
    0.56
     melanch
    0.56
     clowns
    0.55
    Act Density 0.011%

    No Known Activations