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

    Neuronpedia

    INDEX
    Explanations

    finding or suggesting items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Français
    0.47
    In
    0.43
     Barre
    0.41
     Fridge
    0.41
     français
    0.39
    Մ
    0.39
     In
    0.38
    樂
    0.38
     France
    0.38
    悰
    0.37
    POSITIVE LOGITS
    <unused48>
    0.48
     contratos
    0.41
     yearling
    0.41
    <unused2>
    0.40
     pectin
    0.40
    wellery
    0.39
     terão
    0.38
     hewan
    0.38
    <unused79>
    0.38
     কাঠের
    0.38
    Act Density 0.001%

    No Known Activations