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

    Neuronpedia

    INDEX
    Explanations

    simple pleasure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estremamente
    0.90
     extremamente
    0.89
     extrêmement
    0.88
     extremadamente
    0.85
     굉장히
    0.84
     بشكل
    0.81
     bzw
    0.81
     DDoS
    0.78
    굉장
    0.77
     astrophysical
    0.76
    POSITIVE LOGITS
     tales
    0.89
     tale
    0.87
     hearth
    0.80
     toil
    0.80
     deeds
    0.79
     servants
    0.77
     wares
    0.77
     maids
    0.77
     weary
    0.77
     songs
    0.76
    Act Density 0.910%

    No Known Activations