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

    Neuronpedia

    INDEX
    Explanations

    ndon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ()")↵
    -0.07
    ером
    -0.07
     into
    -0.06
     дерев
    -0.06
    '})↵
    -0.06
     doldur
    -0.06
     yapıl
    -0.06
     inhibition
    -0.06
    bairro
    -0.06
    ères
    -0.06
    POSITIVE LOGITS
    BJ
    0.06
    %B
    0.06
     Johnson
    0.06
     marching
    0.06
    ndon
    0.06
    .bn
    0.06
    .Mask
    0.06
     commend
    0.06
     rng
    0.06
     zoom
    0.06
    Act Density 0.001%

    No Known Activations