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

    Neuronpedia

    INDEX
    Explanations

    enjoy and relax activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     müsste
    0.44
     emphasise
    0.41
     WANTED
    0.40
    ⊡
    0.40
    ฏ
    0.39
    চাই
    0.38
     इसे
    0.38
     slabs
    0.37
     racers
    0.37
     dik
    0.37
    POSITIVE LOGITS
     disfrutar
    0.81
     disfrut
    0.74
     disfruta
    0.73
     relaj
    0.72
    Enjoy
    0.71
     relax
    0.70
     enjoy
    0.69
     Relax
    0.67
     menikmati
    0.67
    enjoy
    0.67
    Act Density 0.011%

    No Known Activations