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

    Neuronpedia

    INDEX
    Explanations

    Kam, plak, Lang, immun, Brandon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jose
    0.82
    cester
    0.81
     rome
    0.81
     Romano
    0.78
     কাক
    0.78
     CTE
    0.77
    JOSE
    0.75
     CCI
    0.75
     Bosco
    0.74
     Tile
    0.74
    POSITIVE LOGITS
     Cliff
    0.99
    Cliff
    0.89
     Alt
    0.87
    Golf
    0.86
     Baird
    0.86
    alt
    0.85
    Inf
    0.83
    inf
    0.83
     Goldberg
    0.83
    راف
    0.82
    Act Density 1.287%

    No Known Activations