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

    Neuronpedia

    INDEX
    Explanations

    how much/many

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     demeanor
    1.14
     ১৫
    1.03
    1
    1.03
    feather
    1.00
    2
    0.96
     suite
    0.94
    0
    0.93
     récente
    0.93
    !.
    0.92
     haute
    0.92
    POSITIVE LOGITS
     benöt
    1.60
     veces
    1.57
     사람들이
    1.46
    інки
    1.46
     repetitions
    1.45
     personer
    1.43
     days
    1.43
     ljudi
    1.41
    ယောက်
    1.40
     Visits
    1.39
    Act Density 0.248%

    No Known Activations