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

    Neuronpedia

    INDEX
    Explanations

    Chinese characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vinyl
    0.72
    6
    0.68
    hom
    0.56
    5
    0.55
    thermal
    0.54
     refrigerant
    0.54
    3
    0.54
    9
    0.54
    0
    0.52
    a
    0.52
    POSITIVE LOGITS
     Charm
    0.54
     Denise
    0.52
     otoño
    0.52
     कोरिया
    0.51
     hermoso
    0.50
     üzerinde
    0.49
     charms
    0.49
    劻
    0.49
     Ю
    0.49
     Adm
    0.48
    Act Density 0.028%

    No Known Activations