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

    Neuronpedia

    INDEX
    Explanations

    Non-natural language text

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
    ande
    -0.07
     Nest
    -0.07
     localhost
    -0.07
     برنامه
    -0.07
     Heaven
    -0.06
     hace
    -0.06
     ons
    -0.06
     Sith
    -0.06
    aaS
    -0.06
     Breaking
    -0.06
    POSITIVE LOGITS
    ！');↵
    0.06
    .va
    0.06
    	item
    0.06
     تول
    0.06
     allure
    0.06
     cyk
    0.06
     mCurrent
    0.06
     पड
    0.06
     mue
    0.06
     سی
    0.06
    Act Density 0.000%

    No Known Activations