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

    Neuronpedia

    INDEX
    Explanations

    years after apostrophe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    徴
    0.39
    кое
    0.38
     ‘
    0.38
    ievements
    0.38
     cute
    0.36
    pounds
    0.35
     Unt
    0.34
    нце
    0.34
    ���
    0.34
    m
    0.34
    POSITIVE LOGITS
     फायदा
    0.45
     Dernière
    0.42
     sufrió
    0.40
    ༨
    0.40
     esfuerzos
    0.39
    0.39
     שנ
    0.38
    ⒎
    0.38
    醎
    0.38
    ៨
    0.37
    Act Density 0.002%

    No Known Activations