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

    Neuronpedia

    INDEX
    Explanations

    corresponding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     дерев
    -0.07
     thousands
    -0.07
     measurements
    -0.06
    .Information
    -0.06
    Overview
    -0.06
     दक
    -0.06
     care
    -0.06
    XF
    -0.06
     Guests
    -0.06
    -six
    -0.06
    POSITIVE LOGITS
     mama
    0.06
    Cantidad
    0.06
    ナル
    0.06
     Constit
    0.06
     Belly
    0.06
     macros
    0.06
     Twig
    0.06
     transports
    0.06
     conveniently
    0.06
    契
    0.06
    Act Density 0.004%

    No Known Activations