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

    Neuronpedia

    INDEX
    Explanations

    brands and personality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﺸ
    0.43
     ENT
    0.39
     قاعدة
    0.38
    entityManager
    0.37
    гія
    0.37
    😊
    0.37
    😀
    0.36
     तरंग
    0.36
     McDonnell
    0.36
    pessoas
    0.36
    POSITIVE LOGITS
     combos
    0.45
     Rodríguez
    0.41
    icc
    0.40
    ital
    0.39
    ).}
    0.38
     принятия
    0.38
     Krebs
    0.38
    atori
    0.38
     heron
    0.38
     hydroxide
    0.37
    Act Density 0.000%

    No Known Activations