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
     snap
    -0.08
    落入
    -0.07
    /chat
    -0.07
     disappearing
    -0.07
     RECORD
    -0.07
     parch
    -0.07
    <form
    -0.07
     Pharm
    -0.06
    .Trim
    -0.06
    	errors
    -0.06
    POSITIVE LOGITS
        
↵    
↵
    0.07
    ว
    0.07
    شاب
    0.06
     *****
    0.06
     Estados
    0.06
    eko
    0.06
    artment
    0.06
     have
    0.06
     competing
    0.06
    高新技术
    0.06
    Act Density 0.000%

    No Known Activations