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

    Neuronpedia

    INDEX
    Explanations

    PM time zone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     епи
    0.40
    SIDE
    0.39
    abhavam
    0.39
     sted
    0.39
     episcop
    0.38
     thrice
    0.38
     BOOKS
    0.38
    窸
    0.38
    大家的
    0.38
    कां
    0.38
    POSITIVE LOGITS
    ，
    0.41
    DMF
    0.40
     ،
    0.37
    RELL
    0.35
     Serp
    0.35
    BorderSize
    0.35
    ingh
    0.35
    াই
    0.34
    LCM
    0.34
    ابط
    0.34
    Act Density 0.000%

    No Known Activations