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

    Neuronpedia

    INDEX
    Explanations

    professions and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    3.02
    erte
    2.84
     bylaws
    2.63
    ities
    2.62
    лго
    2.59
    llam
    2.54
     esperado
    2.51
     adelante
    2.44
    ्य
    2.41
    ًا
    2.40
    POSITIVE LOGITS
    ﺔ
    3.79
    зм
    2.76
    ﻲ
    2.75
    end
    2.72
    <bos>
    2.70
     Cellulose
    2.70
    ского
    2.59
    anglement
    2.52
    ère
    2.52
    ﯽ
    2.51
    Act Density 0.159%

    No Known Activations