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

    Neuronpedia

    INDEX
    Explanations

    poets, musicians, actors, and writers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ποί
    0.44
    imental
    0.39
    dehyde
    0.39
    치가
    0.39
    đer
    0.38
    ቲክ
    0.38
    prene
    0.38
    ratulations
    0.37
     cerebrospinal
    0.36
    зир
    0.36
    POSITIVE LOGITS
     Gam
    0.39
     ~
    0.39
     Configurations
    0.38
     unreachable
    0.38
     Dragon
    0.37
     Did
    0.36
     Zach
    0.36
     gingerbread
    0.36
     Michelangelo
    0.36
    ின
    0.36
    Act Density 0.000%

    No Known Activations