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

    Neuronpedia

    INDEX
    Explanations

    instruction set architecture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     минус
    0.41
    韓国
    0.40
     آفس
    0.40
     malls
    0.38
    挑戦
    0.38
     launch
    0.38
     readjust
    0.38
    ποιη
    0.38
    韓國
    0.37
    ResumeLayout
    0.36
    POSITIVE LOGITS
     opcode
    1.00
     instruction
    0.98
     Instruction
    0.98
    Instruction
    0.98
    instruction
    0.93
    opcode
    0.87
    指令
    0.82
     operands
    0.79
     instruct
    0.73
     Instructions
    0.73
    Act Density 0.024%

    No Known Activations