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

    Neuronpedia

    INDEX
    Explanations

    jar, Jaro, Jari, JARVIS, jarring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Сан
    0.41
     стать
    0.39
    Prayer
    0.38
    таны
    0.38
     تي
    0.38
    パラ
    0.37
     Moto
    0.37
    吳
    0.37
    يكم
    0.37
     laoreet
    0.36
    POSITIVE LOGITS
     jar
    0.64
     Jar
    0.64
    Jar
    0.61
     JAR
    0.58
    jar
    0.54
     jars
    0.47
     jarring
    0.46
     Ingers
    0.42
     Ingersoll
    0.42
    JAR
    0.41
    Act Density 0.001%

    No Known Activations