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

    Neuronpedia

    INDEX
    Explanations

    previous / last / name matching

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OND
    0.98
    NING
    0.95
    ر
    0.95
    1
    0.92
    to
    0.90
    TO
    0.90
     ಯಾವುದೇ
    0.89
    哪
    0.89
    AP
    0.88
    AG
    0.88
    POSITIVE LOGITS
     oeuvre
    0.99
    parvec
    0.97
     chaîne
    0.96
     sehen
    0.96
     isotype
    0.94
     accueil
    0.93
     தொலை
    0.92
     یافته
    0.91
     interfacing
    0.90
     ramai
    0.90
    Act Density 0.002%

    No Known Activations