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

    Neuronpedia

    INDEX
    Explanations

    .layers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    useum
    -0.07
    ebilirsiniz
    -0.07
    ющего
    -0.06
     LOC
    -0.06
     dle
    -0.05
    :.:.:
    -0.05
     Murdoch
    -0.05
     Rol
    -0.05
     ------------------------------------------------------------------------↵
    -0.05
     lipstick
    -0.05
    POSITIVE LOGITS
     устан
    0.07
    .layers
    0.07
    kbd
    0.07
    Accessory
    0.06
     ',',
    0.06
    О
    0.06
     пропози
    0.06
    важа
    0.06
     बज
    0.06
     клас
    0.06
    Act Density 0.001%

    No Known Activations