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

    Neuronpedia

    INDEX
    Explanations

    say to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     brun
    -0.06
    _network
    -0.06
     rubble
    -0.06
    愿
    -0.06
     Sidd
    -0.06
    .opend
    -0.06
    Extent
    -0.06
     covenant
    -0.06
    Vector
    -0.06
     мод
    -0.06
    POSITIVE LOGITS
    ・━・━・━・━
    0.07
     Lik
    0.07
    -between
    0.07
    Tv
    0.07
     :)
    0.07
    OM
    0.06
     [])
    0.06
    genres
    0.06
     sprav
    0.06
    .AddModelError
    0.06
    Act Density 0.028%

    No Known Activations