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

    Neuronpedia

    INDEX
    Explanations

    Section headers and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Kingdom
    0.72
    stat
    0.68
    ric
    0.64
    to
    0.59
    card
    0.59
    ate
    0.58
    cy
    0.58
     ilus
    0.58
    렬
    0.58
    lic
    0.57
    POSITIVE LOGITS
    氇
    1.00
     Mga
    0.98
    ﺮ
    0.98
    觕
    0.96
    ܙ
    0.96
     История
    0.92
     Amenities
    0.92
    艐
    0.91
     Cách
    0.89
     約
    0.88
    Act Density 0.000%

    No Known Activations