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

    Neuronpedia

    INDEX
    Explanations

    latex mathematical formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     निर्णायक
    0.41
    豁
    0.40
     relief
    0.38
    мыш
    0.37
    閱
    0.37
    success
    0.37
     valign
    0.37
    outlook
    0.37
    Aux
    0.36
     rel
    0.36
    POSITIVE LOGITS
     Mathematics
    0.56
    公式
    0.54
     formulas
    0.52
     Formula
    0.50
     math
    0.48
     फार्मूला
    0.48
     mathematical
    0.48
     mathematics
    0.48
     Mathematical
    0.48
     matemat
    0.47
    Act Density 0.014%

    No Known Activations