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

    Neuronpedia

    INDEX
    Explanations

    names like Francis and Franz

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    齋
    0.44
     вести
    0.44
     FLEX
    0.42
     jusque
    0.40
    Доб
    0.40
     flex
    0.39
    𝒎
    0.39
    لسط
    0.39
    ரசுக்
    0.39
    дай
    0.38
    POSITIVE LOGITS
     Xavier
    0.66
    ische
    0.45
    iska
    0.43
     X
    0.41
    isk
    0.39
    सीसी
    0.38
    cus
    0.38
    X
    0.38
    িস
    0.37
    чением
    0.37
    Act Density 0.004%

    No Known Activations