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

    Neuronpedia

    INDEX
    Explanations

    reason why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ရေး
    0.51
     বিষয়ক
    0.51
    ገድ
    0.48
     concerne
    0.48
    ваемых
    0.47
    リーン
    0.47
    သုံး
    0.47
     phony
    0.47
     られ
    0.46
    ymptotic
    0.46
    POSITIVE LOGITS
    Id
    0.45
    ulas
    0.44
    s
    0.43
    uts
    0.42
    appa
    0.42
     hepat
    0.42
     εί
    0.42
     inquiries
    0.41
    <0x88>
    0.41
    詢
    0.39
    Act Density 0.000%

    No Known Activations