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

    Neuronpedia

    INDEX
    Explanations

    principle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     principle
    -1.66
    principle
    -1.52
     Principle
    -1.48
    Principle
    -1.25
     PRINCIP
    -1.13
     principles
    -1.13
     Principles
    -0.99
    principles
    -0.98
     princi
    -0.96
     Prinzip
    -0.88
    POSITIVE LOGITS
    d
    0.77
    Datuak
    0.58
    dun
    0.51
    lander
    0.50
    न्त
    0.50
    SpringBootTest
    0.49
     judgment
    0.49
    ising
    0.48
    anting
    0.48
    n
    0.48
    Act Density 0.173%

    No Known Activations