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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    374
    -0.07
    289
    -0.07
    頂
    -0.07
     چرا
    -0.06
    getID
    -0.06
    nv
    -0.06
     Directed
    -0.06
    .W
    -0.06
    imagem
    -0.06
    ева
    -0.06
    POSITIVE LOGITS
    ]='\
    0.09
    )=
    0.08
    ']=
    0.08
     percentage
    0.07
    aepernick
    0.07
     исход
    0.07
     $\
    0.07
    =-
    0.07
    ={↵
    0.07
     africa
    0.07
    Act Density 0.014%

    No Known Activations