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

    Neuronpedia

    INDEX
    Explanations

    language introduction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.45
     आयकर
    0.41
    ৤
    0.40
    ਜ਼
    0.40
    逅
    0.39
    збе
    0.39
    嵐
    0.39
    注明
    0.38
    ພາບ
    0.37
    Œ
    0.37
    POSITIVE LOGITS
     kw
    0.41
    ma
    0.36
    ula
    0.35
     woman
    0.35
    kw
    0.35
     Kw
    0.35
    <0xEA>
    0.34
    гъ
    0.34
     people
    0.34
    nu
    0.33
    Act Density 0.008%

    No Known Activations