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

    Neuronpedia

    INDEX
    Explanations

    coco coir, Linux, Polenta

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    heuristic
    0.40
    DOCKED
    0.38
    ZrO
    0.37
     memorable
    0.37
    好
    0.37
     berkel
    0.36
    ாரம்
    0.36
    toLowerCase
    0.35
     Kxe
    0.35
    Sag
    0.35
    POSITIVE LOGITS
     পুজ
    0.39
     जुड़ी
    0.39
    𒉿
    0.39
     Korea
    0.38
    _{*}\
    0.38
     celtic
    0.38
     korean
    0.38
     Koreans
    0.38
     Пів
    0.38
    <0x9D>
    0.37
    Act Density 0.000%

    No Known Activations