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

    Neuronpedia

    INDEX
    Explanations

    others can modify or use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     other
    0.70
     другого
    0.60
     മറ്റൊരു
    0.57
    IO
    0.57
    other
    0.57
     其他
    0.57
     andet
    0.56
    0.56
     autre
    0.55
     Other
    0.54
    POSITIVE LOGITS
     подобных
    0.49
    comers
    0.47
     tantos
    0.47
    лся
    0.45
    ંપની
    0.44
    celi
    0.43
    を守
    0.43
    馳
    0.42
     подобные
    0.42
    \%),
    0.42
    Act Density 0.007%

    No Known Activations