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

    Neuronpedia

    INDEX
    Explanations

    Page or reference numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	resource
    -0.07
     дві
    -0.07
    冠
    -0.06
     万元
    -0.06
    ्डल
    -0.06
    襲
    -0.06
    	O
    -0.06
    erus
    -0.06
     طریق
    -0.06
     giàu
    -0.06
    POSITIVE LOGITS
    _pll
    0.07
    mods
    0.06
     newY
    0.06
    |=↵
    0.06
    >(()
    0.06
    ливо
    0.06
     overlook
    0.06
    .Cluster
    0.06
    　ゝ
    0.06
    =↵↵
    0.06
    Act Density 0.001%

    No Known Activations