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

    Neuronpedia

    INDEX
    Explanations

    code snippets and commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    एक
    1.21
    <em>
    1.05
     Também
    1.05
    aneously
    0.95
     Sebuah
    0.94
    kuensi
    0.91
     Yours
    0.91
     quello
    0.91
    မ
    0.91
     Yaad
    0.90
    POSITIVE LOGITS
    /
    0.84
    *
    0.75
     docker
    0.73
     GitHub
    0.71
     Docker
    0.71
    de
    0.70
    \
    0.70
     dplyr
    0.70
    et
    0.70
    +
    0.69
    Act Density 0.262%

    No Known Activations