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

    Neuronpedia

    INDEX
    Explanations

    rule them all

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    еха
    0.38
    ]<<"
    0.36
     washing
    0.35
    assurer
    0.35
    Assured
    0.35
    ophys
    0.35
    0.34
     bearings
    0.34
     বক্ত
    0.34
    assic
    0.33
    POSITIVE LOGITS
     rule
    1.52
     Rule
    1.41
    Rule
    1.34
     правило
    1.32
    rule
    1.30
     RULE
    1.27
    RULE
    1.16
     regla
    1.05
     regra
    0.98
     रूल
    0.98
    Act Density 0.001%

    No Known Activations