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

    Neuronpedia

    INDEX
    Explanations

    Here's a breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𒋻
    0.41
     triángulos
    0.40
    ➌
    0.40
    పోయే
    0.39
     agacch
    0.39
     thermocouple
    0.39
     drills
    0.38
    埝
    0.38
     adhipp
    0.37
     ajustar
    0.37
    POSITIVE LOGITS
    ]
    0.51
    <sup>
    0.50
    [
    0.46
     Wikipedia
    0.45
    Wikipedia
    0.42
    1
    0.42
    References
    0.41
    ˈ
    0.41
    '
    0.40
    wiki
    0.39
    Act Density 0.052%

    No Known Activations