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

    Neuronpedia

    INDEX
    Explanations

    raid or crackdowns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Что
    0.66
     trở
    0.66
    吸引
    0.66
    成为
    0.65
     hấp
    0.64
     બાળક
    0.64
    が決
    0.64
     attracted
    0.63
     പ്രശ്
    0.63
     becoming
    0.63
    POSITIVE LOGITS
     indiscrimin
    0.90
     innocent
    0.89
     raids
    0.88
     raid
    0.82
     merciless
    0.80
     Raid
    0.77
     unsuspecting
    0.77
     हमला
    0.74
     monastery
    0.74
     monaster
    0.74
    Act Density 0.347%

    No Known Activations