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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Expertise
    0.70
     Experience
    0.65
     Instead
    0.64
     അദ്ദേഹ
    0.63
    Instead
    0.63
     Bacteriol
    0.63
     হয়েছিল
    0.62
     prestigious
    0.62
     Exit
    0.61
     Millions
    0.60
    POSITIVE LOGITS
     любит
    0.80
     ukulele
    0.78
     loves
    0.77
     vinho
    0.75
     hobbies
    0.75
    睡觉
    0.72
     crafty
    0.72
     canciones
    0.71
     daydream
    0.71
     karaoke
    0.70
    Act Density 0.302%

    No Known Activations