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

    Neuronpedia

    INDEX
    Explanations

    asking about satisfaction and improvement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gigantes
    0.92
    massive
    0.90
     massive
    0.90
     colossal
    0.88
     нюан
    0.85
     luscious
    0.85
     hideous
    0.84
     puissant
    0.82
     myriad
    0.80
     tireless
    0.80
    POSITIVE LOGITS
     obecnie
    1.20
     (%)
    1.11
     ≥
    1.10
     personally
    1.09
     regularly
    1.06
     currently
    1.05
    至少
    1.05
     actualmente
    1.00
     monthly
    0.99
     &/
    0.97
    Act Density 0.047%

    No Known Activations