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

    Neuronpedia

    INDEX
    Explanations

    fence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dylan
    -0.07
     Blick
    -0.06
    (cmd
    -0.06
     diabetes
    -0.06
    print
    -0.06
     english
    -0.06
     Astr
    -0.06
    &gt
    -0.06
    .Art
    -0.06
    374
    -0.06
    POSITIVE LOGITS
     fence
    0.08
     cage
    0.08
     Higgins
    0.07
     Enc
    0.07
    _pes
    0.07
    _fence
    0.07
    -backed
    0.07
     EZ
    0.07
     Fence
    0.07
    防
    0.07
    Act Density 0.004%

    No Known Activations