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

    Neuronpedia

    INDEX
    Explanations

    subject matter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     addCriterion
    0.43
    azard
    0.39
    亚马
    0.38
    付ける
    0.38
    لد
    0.38
    اص
    0.37
     substrates
    0.37
    ابان
    0.37
    लर
    0.37
    氀
    0.37
    POSITIVE LOGITS
     matter
    1.61
    matter
    1.36
     Matter
    1.27
    Matter
    1.23
     MATTER
    1.19
    ively
    0.92
    ivities
    0.89
    ivity
    0.87
     मैटर
    0.84
    ivism
    0.78
    Act Density 0.035%

    No Known Activations