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

    Neuronpedia

    INDEX
    Explanations

    instructions and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ljub
    0.50
     Reservation
    0.46
    氹
    0.45
     Pediatric
    0.45
    鲽
    0.45
    新能源
    0.44
    ってた
    0.44
     recip
    0.43
    werben
    0.43
    нче
    0.43
    POSITIVE LOGITS
    naires
    0.54
    意
    0.49
     evade
    0.48
    Preface
    0.45
     grievances
    0.45
     payloads
    0.44
     exce
    0.44
    Th
    0.44
    ет
    0.44
     scars
    0.44
    Act Density 0.000%

    No Known Activations