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

    Neuronpedia

    INDEX
    Explanations

    trauma and weaknesses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     towering
    0.48
    7
    0.43
     humoral
    0.41
     limitation
    0.41
    actose
    0.40
    5
    0.40
    9
    0.39
     impair
    0.39
     tower
    0.39
     shortening
    0.39
    POSITIVE LOGITS
    长
    0.50
    枺
    0.48
    䞍
    0.47
    制造业
    0.46
    窨
    0.45
    ت
    0.45
    ู
    0.44
    на
    0.43
    و
    0.43
    比利
    0.43
    Act Density 0.013%

    No Known Activations