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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    删除
    -0.06
     cargar
    -0.06
    ....↵↵
    -0.06
     호
    -0.06
    Helmet
    -0.06
    toMatchSnapshot
    -0.06
    Cleanup
    -0.06
     embrace
    -0.06
     journals
    -0.06
    /terms
    -0.06
    POSITIVE LOGITS
     rebel
    0.08
    ben
    0.07
     Spr
    0.07
    %"
    0.07
    joined
    0.07
    .GetAll
    0.07
     fright
    0.07
    itle
    0.06
     START
    0.06
     gets
    0.06
    Act Density 0.027%

    No Known Activations