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

    Neuronpedia

    INDEX
    Explanations

    anger and flames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     लागे
    0.74
    슭
    0.68
     zeich
    0.66
    陟
    0.66
    ϱ
    0.66
    Polynomial
    0.64
     Hyg
    0.64
     אור
    0.63
    plication
    0.62
    纶
    0.62
    POSITIVE LOGITS
     anger
    3.47
     angry
    3.19
     rage
    3.01
     enraged
    2.79
     angrily
    2.61
     Anger
    2.61
     fury
    2.61
     angered
    2.56
    愤怒
    2.52
     resentment
    2.48
    Act Density 0.675%

    No Known Activations