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

    Neuronpedia

    INDEX
    Explanations

    diagramming or code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تصور
    0.40
     보통
    0.39
     چاہتے
    0.36
    ത്തോ
    0.35
     Olympia
    0.34
    霝
    0.34
    䁂
    0.34
     लॉक
    0.34
     Forever
    0.34
     BUS
    0.33
    POSITIVE LOGITS
    Subject
    0.43
    権利
    0.42
    ⓘ
    0.42
    融资
    0.40
    Physical
    0.39
    Descrição
    0.37
    묘
    0.37
    Notes
    0.37
    Subjects
    0.37
    Permissions
    0.37
    Act Density 0.000%

    No Known Activations