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

    Neuronpedia

    INDEX
    Explanations

    that was it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     اف
    0.37
    নকে
    0.36
    アフ
    0.36
     ullamco
    0.35
    infodisc
    0.35
    ⧐
    0.35
    íž
    0.34
    graphHead
    0.34
    葡
    0.34
    𝓃
    0.34
    POSITIVE LOGITS
     Thats
    1.85
     thats
    1.80
    thats
    1.70
    Thats
    1.64
    That
    1.55
     That
    1.54
     đó
    1.27
     THAT
    1.27
     दैट
    1.27
    THAT
    1.16
    Act Density 0.162%

    No Known Activations