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

    Neuronpedia

    INDEX
    Explanations

    Who questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝐧
    1.80
    𝐫
    1.77
    nya
    1.76
    ting
    1.70
    𝐭
    1.66
    𝐚
    1.65
    ts
    1.65
    tyle
    1.65
    tr
    1.63
    mi
    1.62
    POSITIVE LOGITS
    opee
    1.77
     විසින්
    1.77
    1.77
    ள்ளை
    1.77
     صاحب
    1.75
    iensis
    1.70
     Whom
    1.69
    й
    1.67
    おります
    1.66
    ಿ
    1.64
    Act Density 0.197%

    No Known Activations