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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     liqu
    -0.07
    -0.07
    -based
    -0.07
     phases
    -0.07
     synopsis
    -0.07
     torn
    -0.07
    พบ
    -0.07
    ॉक
    -0.06
     mentioning
    -0.06
    购
    -0.06
    POSITIVE LOGITS
    						↵
    0.07
    :flutter
    0.07
    ？”↵↵
    0.06
    								↵
    0.06
    [];↵↵
    0.06
    (":
    0.06
            
↵        
↵
    0.06
    ="#">↵
    0.06
    ें।↵
    0.06
    				↵
    0.06
    Act Density 0.061%

    No Known Activations