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

    Neuronpedia

    INDEX
    Explanations

    find information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Otros
    0.96
    Autres
    0.86
    ၻ
    0.85
    Chúng
    0.85
    Nuestro
    0.84
     Alguns
    0.84
    Weitere
    0.83
    Its
    0.83
    Thats
    0.83
    Unsere
    0.80
    POSITIVE LOGITS
     the
    0.53
     earthquake
    0.51
     residential
    0.50
     brain
    0.49
     a
    0.48
     airport
    0.47
     spinal
    0.47
     chicken
    0.46
     shuffle
    0.46
     facial
    0.46
    Act Density 3.734%

    No Known Activations