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

    Neuronpedia

    INDEX
    Explanations

    domain names followed by slashes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     -
    0.53
    施術
    0.53
    okus
    0.52
    -.
    0.51
     lie
    0.51
     Inca
    0.51
    -*
    0.50
    ↵↵
    0.49
     ukulele
    0.48
     Torah
    0.48
    POSITIVE LOGITS
    /...
    0.78
    /
    0.67
    /@
    0.67
    /%
    0.65
    /__
    0.65
    Concept
    0.63
    ваем
    0.61
    +/
    0.61
    Integr
    0.58
    ವು
    0.58
    Act Density 0.228%

    No Known Activations