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

    Neuronpedia

    INDEX
    Explanations

    rules and procedures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ạc
    0.42
    褔
    0.42
    InvariantCulture
    0.40
    䒿
    0.40
     setattr
    0.40
    feels
    0.39
     ayah
    0.39
    落ち着
    0.39
    popUp
    0.38
    DefineConstants
    0.38
    POSITIVE LOGITS
     Rules
    0.98
    Rules
    0.86
     Rule
    0.82
     RULES
    0.76
     rules
    0.74
    Rule
    0.74
     pleading
    0.72
    规则
    0.70
     Courts
    0.68
     règles
    0.68
    Act Density 0.004%

    No Known Activations