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

    Neuronpedia

    INDEX
    Explanations

    this statement is false

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dumbbells
    0.45
     algum
    0.41
    璿
    0.41
     laces
    0.40
     LAY
    0.40
     sprinkle
    0.39
     waarbij
    0.39
    ITERATURE
    0.39
     WordPerfect
    0.39
     sciatica
    0.38
    POSITIVE LOGITS
    Это
    0.54
     هذا
    0.53
     этого
    0.52
     this
    0.52
    this
    0.52
     это
    0.52
    这句话
    0.51
    <b>
    0.51
    Esto
    0.50
    This
    0.49
    Act Density 0.004%

    No Known Activations