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

    Neuronpedia

    INDEX
    Explanations

    instructions and guides

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     débat
    0.89
     debate
    0.78
     Debate
    0.77
     phenotypes
    0.77
     debating
    0.75
    debate
    0.73
     debates
    0.71
    دید
    0.70
     पकड़
    0.68
     Renner
    0.66
    POSITIVE LOGITS
     instructions
    5.25
     Instructions
    4.93
    instructions
    4.85
    Instructions
    4.81
     instruction
    4.77
     Instruction
    4.47
    Instruction
    4.40
    instruction
    4.34
     instrucciones
    4.10
     instruções
    3.99
    Act Density 0.813%

    No Known Activations