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

    Neuronpedia

    INDEX
    Explanations

    maths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    и
    1.70
    SAR
    1.61
     través
    1.57
    میں
    1.49
    де
    1.47
    اد
    1.47
    ात
    1.47
    Sementara
    1.47
    Depuis
    1.40
    걍
    1.40
    POSITIVE LOGITS
    ない
    1.91
    밂
    1.67
     pudd
    1.58
    aclysm
    1.52
     inoculated
    1.50
    вары
    1.45
    有所
    1.41
     gauging
    1.39
     Bols
    1.37
    一口
    1.35
    Act Density 0.001%

    No Known Activations