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

    Neuronpedia

    INDEX
    Explanations

    disappointment and loss

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     control
    0.42
     stochastic
    0.42
     focus
    0.41
     sync
    0.41
     alpha
    0.40
     +/-
    0.40
     controlling
    0.40
    控制
    0.39
     warp
    0.39
    制御
    0.39
    POSITIVE LOGITS
     disappointment
    0.96
     sadness
    0.88
     heartbreak
    0.87
     kehilangan
    0.87
     perdita
    0.86
    损失
    0.84
    失去
    0.84
     disappointed
    0.83
     disappointing
    0.83
     disappointments
    0.82
    Act Density 0.149%

    No Known Activations