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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    โ
    -0.07
    Visualization
    -0.07
     incidental
    -0.07
    👌
    -0.07
    📥
    -0.07
    荣誉称号
    -0.07
     אירועים
    -0.07
    ḳ
    -0.06
    三代
    -0.06
     recipro
    -0.06
    POSITIVE LOGITS
     Hungary
    0.07
    石家庄
    0.07
    System
    0.07
     Signals
    0.07
     Homes
    0.07
    Ｄ
    0.07
    	tr
    0.07
     peak
    0.06
    强调
    0.06
     militias
    0.06
    Act Density 0.000%

    No Known Activations