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

    Neuronpedia

    INDEX
    Explanations

    offering support

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ان
    0.95
    Jogo
    0.75
    Hej
    0.73
    UTTON
    0.72
     部
    0.72
     tainted
    0.70
    ש
    0.70
    나
    0.70
     superseded
    0.69
     Altos
    0.68
    POSITIVE LOGITS
    is
    1.08
    ia
    1.01
    ó
    1.00
    ut
    0.97
    ok
    0.95
     sostegno
    0.93
    iv
    0.89
     nurt
    0.89
     SUPPORT
    0.89
     Support
    0.88
    Act Density 0.011%

    No Known Activations