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

    Neuronpedia

    INDEX
    Explanations

    . OK

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ത്തി
    0.63
    tuned
    0.62
     extracted
    0.62
     capa
    0.62
     optional
    0.61
    extracted
    0.61
    जेक्ट
    0.60
     tyle
    0.60
     নির্যা
    0.60
     and
    0.60
    POSITIVE LOGITS
    .=
    0.92
    .,
    0.91
    Accent
    0.89
    ./
    0.89
    .),
    0.89
    .$,
    0.88
    ,)
    0.87
    AddTask
    0.86
    ™.
    0.86
     বলিতে
    0.84
    Act Density 0.352%

    No Known Activations