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

    Neuronpedia

    INDEX
    Explanations

    therapist?quivering?weaklings.company_id

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     theseKeys
    1.41
     submanifold
    1.37
    ſe
    1.36
    ァ
    1.35
     striées
    1.30
    owneri
    1.28
     shuffled
    1.28
     Nghị
    1.27
     ਇਸ
    1.27
     transom
    1.24
    POSITIVE LOGITS
    >
    1.07
    л
    1.07
    ет
    1.04
     prov
    0.99
    ров
    0.95
    꺼
    0.94
    IN
    0.93
     inger
    0.92
    AH
    0.92
     silo
    0.91
    Act Density 0.001%

    No Known Activations