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

    Neuronpedia

    INDEX
    Explanations

    "

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	UN
    -0.06
     plug
    -0.06
    Sharper
    -0.06
     LOG
    -0.06
    natural
    -0.06
    _nick
    -0.06
    スレ
    -0.06
    	password
    -0.06
     architects
    -0.06
     legally
    -0.06
    POSITIVE LOGITS
    PasswordField
    0.07
     soar
    0.07
     Travis
    0.06
     وفي
    0.06
    /english
    0.06
    ジ
    0.06
    		↵	↵
    0.06
     اتحاد
    0.06
    ียม
    0.06
    idae
    0.06
    Act Density 0.425%

    No Known Activations