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

    Neuronpedia

    INDEX
    Explanations

    mientras

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	out
    -0.08
    _Response
    -0.07
     Baldwin
    -0.06
     Batı
    -0.06
    Có
    -0.06
    _organization
    -0.06
    ола
    -0.06
     intensified
    -0.06
     wid
    -0.06
    Intro
    -0.06
    POSITIVE LOGITS
    mişti
    0.07
    emplate
    0.07
    arseille
    0.06
    those
    0.06
    	Long
    0.06
    								↵
    0.06
    .usage
    0.06
    .Internal
    0.06
     sugars
    0.06
     داشتند
    0.06
    Act Density 0.008%

    No Known Activations