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

    Neuronpedia

    INDEX
    Explanations

    cut and then a noun or verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    2.33
    ⺝
    1.83
     appels
    1.76
    檛
    1.71
    ਰ
    1.70
    ంక
    1.69
    ි
    1.68
    osť
    1.63
    옌
    1.63
    헷
    1.62
    POSITIVE LOGITS
     Cria
    1.79
     তবুও
    1.56
    )
    1.46
    ní
    1.45
    ierrez
    1.45
     बवाल
    1.45
    за
    1.44
     Cutting
    1.42
    umably
    1.42
    tingham
    1.41
    Act Density 0.019%

    No Known Activations