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

    Neuronpedia

    INDEX
    Explanations

    YAML workflow names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     offic
    0.44
    ᓗ
    0.40
    颶
    0.38
    ল্যান্ড
    0.38
     rulemaking
    0.38
     lounge
    0.38
     loy
    0.37
     सलाद
    0.37
     announces
    0.36
     serde
    0.36
    POSITIVE LOGITS
    ravel
    0.45
     ஐந்து
    0.44
     மூன்று
    0.44
    评估
    0.43
    Assess
    0.43
    ribution
    0.41
     tři
    0.41
    ઈ
    0.41
    Crime
    0.40
    is
    0.40
    Act Density 0.001%

    No Known Activations