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

    Neuronpedia

    INDEX
    Explanations

    lists

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     τις
    0.80
     αυτές
    0.74
     этот
    0.73
     τον
    0.70
     Essas
    0.68
     новий
    0.67
     ένας
    0.66
     previstas
    0.65
     которое
    0.64
     feitas
    0.63
    POSITIVE LOGITS
     mayoría
    0.79
     última
    0.73
     famosa
    0.71
     búsqueda
    0.71
     plupart
    0.70
     maioria
    0.70
     misma
    0.69
     historia
    0.68
     línea
    0.66
     nostra
    0.66
    Act Density 0.133%

    No Known Activations