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

    Neuronpedia

    INDEX
    Explanations

    be + past participle or adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    これは
    0.70
     juggle
    0.68
    情報は
    0.66
    navigate
    0.62
     navigate
    0.60
     tinge
    0.60
     catch
    0.60
    HttpContext
    0.59
     decide
    0.58
    内容は
    0.58
    POSITIVE LOGITS
     regarded
    1.03
     placed
    1.01
     enabled
    0.97
     allowed
    0.97
     able
    0.96
     added
    0.93
     considered
    0.92
     included
    0.91
     emphasized
    0.91
     displayed
    0.91
    Act Density 0.165%

    No Known Activations