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

    Neuronpedia

    INDEX
    Explanations

    Text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    utherland
    -0.07
    培训
    -0.07
     incentive
    -0.07
     thảo
    -0.06
    ́t
    -0.06
     happiest
    -0.06
     obrig
    -0.06
     ulus
    -0.06
     Garc
    -0.06
     CDDL
    -0.06
    POSITIVE LOGITS
    рив
    0.07
    ró
    0.07
    .pos
    0.07
    中國
    0.07
    .hy
    0.07
     RE
    0.07
    (Art
    0.07
     Exhibition
    0.06
    .fig
    0.06
    gende
    0.06
    Act Density 0.000%

    No Known Activations