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

    Neuronpedia

    INDEX
    Explanations

    described by context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rodean
    0.20
     Ό
    0.19
    Hang
    0.18
     {\
    0.18
    Ronald
    0.18
    steil
    0.17
    ತಿ
    0.17
    G
    0.16
    robots
    0.16
    S
    0.16
    POSITIVE LOGITS
     by
    0.32
     oleh
    0.29
     توسط
    0.25
    ByUser
    0.25
     bởi
    0.25
     бит
    0.23
     enough
    0.23
     variously
    0.23
    ependent
    0.23
    ly
    0.22
    Act Density 0.244%

    No Known Activations