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

    Neuronpedia

    INDEX
    Explanations

    immune cells

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     использовали
    0.40
    secondary
    0.39
     permite
    0.39
    火
    0.38
     oferece
    0.38
     کرے
    0.38
     abrió
    0.38
     introduces
    0.37
     Casi
    0.37
    を使
    0.37
    POSITIVE LOGITS
     play
    0.66
     within
    0.63
    play
    0.57
     WITHIN
    0.55
    Play
    0.52
     Within
    0.52
    Within
    0.51
    プレイ
    0.51
     Play
    0.49
    within
    0.47
    Act Density 0.003%

    No Known Activations