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

    Neuronpedia

    INDEX
    Explanations

    EPA

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Poker
    -0.06
    883
    -0.06
     governmental
    -0.06
    Boston
    -0.06
     respectfully
    -0.06
     staffing
    -0.06
     plaintiff
    -0.06
     domestic
    -0.06
     Nothing
    -0.06
    276
    -0.06
    POSITIVE LOGITS
     πως
    0.07
    .transitions
    0.07
     couple
    0.07
    Û
    0.06
    	Vec
    0.06
    PTR
    0.06
    Screen
    0.06
    "/>.↵
    0.06
     subsidized
    0.06
     �
    0.06
    Act Density 0.090%

    No Known Activations