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

    Neuronpedia

    INDEX
    Explanations

    inflammation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ക്കൾ
    1.62
    ところが
    1.59
    队的
    1.57
    threatening
    1.57
     wrestle
    1.56
     deja
    1.55
     поез
    1.53
    ראה
    1.52
    vinced
    1.52
     oras
    1.50
    POSITIVE LOGITS
    er
    1.73
     Bxa
    1.72
    ্পনিক
    1.60
    疹
    1.60
    મ
    1.56
    й
    1.51
     ৫৮
    1.47
    да
    1.43
    થી
    1.43
    ρικ
    1.43
    Act Density 0.074%

    No Known Activations