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

    Neuronpedia

    INDEX
    Explanations

    software installation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tlak
    -0.08
     baby
    -0.06
    ция
    -0.06
    _TOOLTIP
    -0.06
    	row
    -0.06
    橋
    -0.06
     Zurich
    -0.06
     ((!
    -0.06
    /repository
    -0.06
     tập
    -0.06
    POSITIVE LOGITS
    FIG
    0.07
    essen
    0.07
    enh
    0.06
    ंधन
    0.06
    quick
    0.06
     fuels
    0.06
    lessly
    0.06
    diler
    0.06
    onden
    0.06
    .advance
    0.06
    Act Density 0.050%

    No Known Activations