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

    Neuronpedia

    INDEX
    Explanations

    countries and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    string
    0.44
    numeric
    0.44
    delimiter
    0.44
    texture
    0.44
    concatenate
    0.43
    absolute
    0.43
    protein
    0.42
    problem
    0.42
    euler
    0.42
    shrink
    0.42
    POSITIVE LOGITS
     USA
    0.54
     cierra
    0.49
     Prancis
    0.49
     日本
    0.48
     Spanien
    0.47
     Quarry
    0.47
     Italia
    0.46
     Hungary
    0.46
     Frankreich
    0.46
    USA
    0.45
    Act Density 0.321%

    No Known Activations