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

    Neuronpedia

    INDEX
    Explanations

    Mid

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Gu
    0.71
    Ont
    0.71
     Gu
    0.68
    Germ
    0.62
    પાસ
    0.62
     अखिल
    0.61
    authored
    0.61
     Grac
    0.60
     Ont
    0.59
    риев
    0.59
    POSITIVE LOGITS
     শাম
    0.68
     low
    0.64
     품질
    0.62
    range
    0.62
     अच्छा
    0.61
     பத
    0.61
     আধুনিক
    0.61
    レア
    0.61
     chá
    0.60
     جيد
    0.60
    Act Density 0.012%

    No Known Activations