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

    Neuronpedia

    INDEX
    Explanations

    proper noun prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    穵
    0.27
     अराउंड
    0.26
     evam
    0.26
     نہ
    0.25
     Erkrank
    0.25
     BNB
    0.25
    Btns
    0.24
     Margherita
    0.24
    قاف
    0.24
     $%
    0.24
    POSITIVE LOGITS
     tribes
    0.23
     protesters
    0.21
     utilization
    0.21
     konz
    0.21
    expects
    0.20
    ེ་
    0.20
     incorporation
    0.20
    らし
    0.20
    ो
    0.20
    ),]),
    0.19
    Act Density 0.000%

    No Known Activations