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

    Neuronpedia

    INDEX
    Explanations

    causing negative effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ＮＡＮＡ
    0.49
     Crusade
    0.47
    manship
    0.47
     interdiscipl
    0.47
     transcendence
    0.46
     حکومت
    0.46
    igraphic
    0.46
     imbued
    0.45
    armament
    0.44
     peacetime
    0.44
    POSITIVE LOGITS
    e
    0.74
    K
    0.66
    ك
    0.60
    -
    0.57
    le
    0.55
    Y
    0.53
    d
    0.52
    ↵
    0.51
    as
    0.51
    公司
    0.50
    Act Density 0.010%

    No Known Activations