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

    Neuronpedia

    INDEX
    Explanations

    HTML head tag

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ங்கிணை
    1.75
    formerly
    1.73
    landmark
    1.69
    ה
    1.67
    मधील
    1.67
    genstein
    1.65
    )$\
    1.61
    রকম
    1.61
    मध्ये
    1.59
    ../../../
    1.55
    POSITIVE LOGITS
    ल
    2.22
    g
    2.16
    mment
    2.04
    en
    1.98
     siehe
    1.89
    ្នែក
    1.84
    єю
    1.84
    cena
    1.84
     koja
    1.83
     случаи
    1.82
    Act Density 0.003%

    No Known Activations