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

    Neuronpedia

    INDEX
    Explanations

    jag | ja | jar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    elten
    0.40
     Enter
    0.39
     enter
    0.39
     Product
    0.37
    alnya
    0.37
    )?.
    0.37
     Vanilla
    0.37
     extracted
    0.36
     ২৯
    0.36
    നിര
    0.36
    POSITIVE LOGITS
    jar
    0.99
    jan
    0.88
    jars
    0.77
    ja
    0.76
    jat
    0.75
    JAR
    0.74
    jade
    0.72
    jaa
    0.69
    jas
    0.68
    JAN
    0.64
    Act Density 0.001%

    No Known Activations