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

    Neuronpedia

    INDEX
    Explanations

    short

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cy
    -0.07
    ialog
    -0.07
    uctor
    -0.07
    ори
    -0.06
     graduate
    -0.06
     kotlinx
    -0.06
    érique
    -0.06
    pom
    -0.06
    923
    -0.06
    「你
    -0.06
    POSITIVE LOGITS
     sloppy
    0.07
     mockery
    0.07
     shorthand
    0.06
    IRMWARE
    0.06
    ाड
    0.06
    .viewer
    0.06
    strength
    0.06
     корп
    0.06
     ref
    0.06
    odic
    0.06
    Act Density 0.012%

    No Known Activations