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

    Neuronpedia

    INDEX
    Explanations

    year

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ored
    -0.07
    Turning
    -0.07
    לימ
    -0.07
    startup
    -0.07
    irie
    -0.06
     GetUser
    -0.06
    تفاع
    -0.06
     IMS
    -0.06
    רקע
    -0.06
    ween
    -0.06
    POSITIVE LOGITS
    どころ
    0.07
    𫇭
    0.06
    哈尔滨
    0.06
     Rog
    0.06
    .desc
    0.06
    辅
    0.06
    哪
    0.06
     الدوري
    0.06
    擘
    0.06
     intervention
    0.06
    Act Density 0.034%

    No Known Activations