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

    Neuronpedia

    INDEX
    Explanations

    physics and mathematical formalism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cic
    0.76
    이버
    0.75
    entend
    0.71
    罔
    0.67
    जिक
    0.67
     hyperlocal
    0.66
    राजस्थान
    0.65
     variables
    0.65
     вось
    0.65
     sustainably
    0.64
    POSITIVE LOGITS
     formalism
    1.14
     elegance
    1.08
     perturbative
    1.07
     physicists
    1.06
     predictions
    1.05
     elegant
    1.02
     intuition
    1.01
     élég
    1.01
     kinemat
    0.98
     elegan
    0.97
    Act Density 0.214%

    No Known Activations