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

    Neuronpedia

    INDEX
    Explanations

    betrayal and regret

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     shenanigans
    0.54
     uptick
    0.50
     nifty
    0.49
     chewy
    0.49
     spruce
    0.46
     foray
    0.45
     wacky
    0.45
     Nervous
    0.45
     নানান
    0.45
     tricky
    0.44
    POSITIVE LOGITS
    😔
    0.56
    💔
    0.55
     betray
    0.47
     betrayal
    0.46
    😭😭
    0.46
     coldly
    0.45
    😢
    0.45
    Damn
    0.44
     afraid
    0.43
     betrayed
    0.43
    Act Density 0.025%

    No Known Activations