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

    Neuronpedia

    INDEX
    Explanations

    subsidiarity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     electorate
    -0.08
    .euler
    -0.08
    tação
    -0.08
     sanding
    -0.08
     courting
    -0.08
    ments
    -0.08
    components
    -0.08
     grit
    -0.08
     causes
    -0.07
    nuts
    -0.07
    POSITIVE LOGITS
     principle
    0.14
     Principle
    0.14
    原则
    0.14
    Princip
    0.12
     princípio
    0.11
     Prinzip
    0.11
     prinsip
    0.11
     principe
    0.11
     принцип
    0.10
     principes
    0.10
    Act Density 0.012%

    No Known Activations