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

    Neuronpedia

    INDEX
    Explanations

    " is or "

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ットン
    0.25
    Britt
    0.24
    전히
    0.24
    Bowling
    0.24
    atham
    0.24
    Butyl
    0.23
    稟
    0.22
    0.22
    Eppo
    0.22
    ၞ
    0.22
    POSITIVE LOGITS
    0.29
     statuses
    0.26
     Status
    0.24
     /*
    0.23
     ;
    0.23
     status
    0.23
     Form
    0.23
     .
    0.23
     Ratio
    0.22
     Album
    0.22
    Act Density 0.026%

    No Known Activations