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

    Neuronpedia

    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ULAR
    -0.07
    Ted
    -0.07
     ekran
    -0.07
    -catching
    -0.06
    uiltin
    -0.06
    oteric
    -0.06
     bash
    -0.06
     players
    -0.06
    _elt
    -0.06
     winner
    -0.06
    POSITIVE LOGITS
    े�
    0.07
    imary
    0.07
    Disposed
    0.06
    .spatial
    0.06
    Whenever
    0.06
    降
    0.06
    udder
    0.06
    zcze
    0.05
    .grey
    0.05
    051
    0.05
    Act Density 0.009%

    No Known Activations