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

    Neuronpedia

    INDEX
    Explanations

    London, quickly, Administrators, Statistics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }{|
    0.61
    人的
    0.55
    J
    0.53
    공
    0.52
    ان
    0.50
    ته
    0.50
    O
    0.50
    䯩
    0.49
    ச
    0.49
    }{(\
    0.49
    POSITIVE LOGITS
    rian
    0.68
    hensive
    0.57
     vă
    0.55
    rians
    0.54
    rose
    0.52
    žky
    0.52
    riu
    0.52
     linge
    0.52
    rient
    0.51
    rie
    0.51
    Act Density 0.000%

    No Known Activations