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

    Neuronpedia

    INDEX
    Explanations

    Code snippets/data extraction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    frm
    -0.08
     Meg
    -0.07
    Meg
    -0.07
     �
    -0.07
    ulp
    -0.07
    .st
    -0.07
    urst
    -0.07
    �
    -0.07
    ocz
    -0.07
    _var
    -0.07
    POSITIVE LOGITS
     deuren
    0.09
     wkoll
    0.09
     mittlerweile
    0.09
     ժամանակ
    0.09
     დრო
    0.09
     метавонед
    0.09
     समयमा
    0.09
     golpes
    0.09
     governos
    0.08
    [out
    0.08
    Act Density 0.078%

    No Known Activations