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

    Neuronpedia

    INDEX
    Explanations

    don't worry, forget, hesitate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ب
    0.43
    Prof
    0.41
    In
    0.40
    Whenever
    0.39
    वी
    0.38
    ב
    0.38
    語
    0.38
     ஜோ
    0.37
    ลอง
    0.37
     employs
    0.36
    POSITIVE LOGITS
     worry
    0.64
     forget
    0.55
     khawatir
    0.48
     shy
    0.47
     Worry
    0.47
     hesitate
    0.47
    forget
    0.44
     worrying
    0.43
     underestimate
    0.43
     mistake
    0.42
    Act Density 0.014%

    No Known Activations