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

    Neuronpedia

    INDEX
    Explanations

    dissatisfaction with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    0.84
    }$,
    0.65
    ER
    0.62
    }\
    0.61
     ett
    0.61
    ro
    0.60
     for
    0.59
    ema
    0.59
    er
    0.58
     eBay
    0.57
    POSITIVE LOGITS
     discontent
    1.30
     dissatisfaction
    1.12
     dissatisfied
    1.09
     unhappiness
    0.96
     unhappy
    0.84
    ském
    0.75
     dissatisf
    0.74
    ש
    0.74
    ské
    0.73
     dissati
    0.71
    Act Density 0.003%

    No Known Activations