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

    Neuronpedia

    INDEX
    Explanations

    mathematical word problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     parceria
    0.34
     Justices
    0.32
    zości
    0.32
     demokrat
    0.30
     incumb
    0.29
     परिस्थितियों
    0.29
     ন্যায্য
    0.29
     deliberations
    0.29
     Republik
    0.29
     Prison
    0.28
    POSITIVE LOGITS
     а
    0.41
     о
    0.38
    в
    0.38
     в
    0.36
     с
    0.35
     у
    0.34
     р
    0.34
     musst
    0.34
     ५
    0.34
    б
    0.34
    Act Density 0.032%

    No Known Activations