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

    Neuronpedia

    INDEX
    Explanations

    text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     승
    -0.08
     Россий
    -0.07
     jar
    -0.07
     gained
    -0.07
    ambio
    -0.07
    荣
    -0.07
     Abr
    -0.07
     boom
    -0.07
     Jar
    -0.07
     divor
    -0.07
    POSITIVE LOGITS
     text
    0.15
     Text
    0.14
    Text
    0.13
    text
    0.13
    TEXT
    0.11
    	text
    0.11
    /text
    0.11
    .text
    0.11
    _text
    0.11
     texte
    0.10
    Act Density 0.095%

    No Known Activations