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

    Neuronpedia

    INDEX
    Explanations

    math operations and equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     courrier
    0.47
    凛
    0.47
     cynical
    0.45
    sponsor
    0.44
    資格
    0.43
    republik
    0.43
    忠
    0.42
     referrerpolicy
    0.42
    砥
    0.42
     MotoGP
    0.42
    POSITIVE LOGITS
     counting
    0.95
     Counting
    0.91
    Counting
    0.89
     subtraction
    0.88
    counting
    0.78
     multiplication
    0.77
     subtracting
    0.77
     Subtract
    0.77
     subtract
    0.75
     numerals
    0.74
    Act Density 0.043%

    No Known Activations