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

    Neuronpedia

    INDEX
    Explanations

    Amazon, AWS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Milk
    -0.08
     milk
    -0.07
     Cosmetic
    -0.07
     προ
    -0.07
    /documents
    -0.07
    (blob
    -0.07
    artisanlib
    -0.06
    ække
    -0.06
     Reef
    -0.06
    ่านมา
    -0.06
    POSITIVE LOGITS
    تس
    0.06
    ستر
    0.06
    фіка
    0.06
    ulling
    0.06
     incontri
    0.06
    	JOptionPane
    0.06
     nouvel
    0.06
     сир
    0.06
    луж
    0.06
    invitation
    0.06
    Act Density 0.017%

    No Known Activations