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

    Neuronpedia

    INDEX
    Explanations

    observing or seeing nodes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     acon
    0.44
     chitosan
    0.42
     configured
    0.39
     phenols
    0.38
    sticky
    0.37
     alkan
    0.37
     configur
    0.36
    কথ
    0.35
    짚
    0.35
     siv
    0.35
    POSITIVE LOGITS
     Emperor
    0.43
     Premium
    0.42
     Imagery
    0.41
    大众
    0.41
    Imagery
    0.40
    涹
    0.40
     Classical
    0.39
     Emperors
    0.39
     Thirty
    0.38
     Tokyo
    0.38
    Act Density 0.000%

    No Known Activations