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

    Neuronpedia

    INDEX
    Explanations

    structured text labels and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     clerg
    0.53
     Đ
    0.50
     Kirche
    0.48
     cleric
    0.48
     it
    0.47
     DSC
    0.47
     clerical
    0.46
     Damen
    0.46
    데요
    0.45
     Cette
    0.45
    POSITIVE LOGITS
    一丝
    0.47
    ම්
    0.47
    醋
    0.45
     площад
    0.45
    ן
    0.44
    搁
    0.44
    )).
    0.43
    Historically
    0.43
    ד
    0.43
     сексуа
    0.42
    Act Density 0.000%

    No Known Activations