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

    Neuronpedia

    INDEX
    Explanations

    cute / adorable

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vo
    0.98
     Vo
    0.77
    Vo
    0.73
     во
    0.64
    vo
    0.59
     могли
    0.54
     mogao
    0.51
     мог
    0.43
     Could
    0.43
    aisi
    0.42
    POSITIVE LOGITS
    น่า
    2.06
     น่า
    1.75
     đáng
    1.20
     adorable
    0.97
    Adorable
    0.85
    adorable
    0.78
    可愛
    0.74
    可爱
    0.67
     cute
    0.66
     dever
    0.66
    Act Density 0.000%

    No Known Activations