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

    Neuronpedia

    INDEX
    Explanations

    research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     subtraction
    -0.06
    setBackground
    -0.06
    :green
    -0.06
    Bool
    -0.06
     refuses
    -0.06
    agnar
    -0.06
     Subtract
    -0.05
    .sha
    -0.05
    .quantity
    -0.05
     meanwhile
    -0.05
    POSITIVE LOGITS
     embry
    0.07
        
    0.07
     дост
    0.07
     дух
    0.06
    NETWORK
    0.06
    isha
    0.06
    (si
    0.06
    .obtain
    0.06
    944
    0.06
     traffic
    0.06
    Act Density 0.004%

    No Known Activations