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

    Neuronpedia

    INDEX
    Explanations

    tool

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     名
    0.43
     非常
    0.41
     NOMBRE
    0.41
    𝟮
    0.40
    Ạ
    0.40
     📫
    0.39
     toes
    0.39
     yea
    0.38
    ياب
    0.38
     fonctions
    0.38
    POSITIVE LOGITS
    ;">
    0.44
    Click
    0.41
    ">
    0.41
    Swiss
    0.40
     Windows
    0.40
    MouseButton
    0.39
    Clique
    0.39
    click
    0.39
    *
    0.39
    Windows
    0.39
    Act Density 0.030%

    No Known Activations