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

    Neuronpedia

    INDEX
    Explanations

    Natural Language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    device
    -0.07
    reement
    -0.07
    itis
    -0.07
     Prom
    -0.07
    utz
    -0.07
     ResponseEntity
    -0.07
     Butler
    -0.06
     vững
    -0.06
    encers
    -0.06
    XmlAttribute
    -0.06
    POSITIVE LOGITS
    .ns
    0.07
     saison
    0.06
    ，那
    0.06
    _MISS
    0.06
    MOVED
    0.06
    egration
    0.06
     >>=
    0.06
     его
    0.06
    .InnerText
    0.06
     รอง
    0.06
    Act Density 0.119%

    No Known Activations