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

    Neuronpedia

    INDEX
    Explanations

    Here's a table

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    াবা
    0.71
    잍
    0.67
     digits
    0.63
     finite
    0.63
     toner
    0.63
     Colts
    0.62
     outsole
    0.62
     丿
    0.62
     toes
    0.61
     firm
    0.61
    POSITIVE LOGITS
    Alle
    0.79
    vehicles
    0.77
    Veh
    0.74
     सदा
    0.73
    towards
    0.73
    Alban
    0.72
    versus
    0.71
    with
    0.69
    Aless
    0.68
    Versions
    0.68
    Act Density 0.102%

    No Known Activations