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

    Neuronpedia

    INDEX
    Explanations

    punctuations and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    焼
    0.43
    規模
    0.43
     ниже
    0.42
     brachial
    0.42
    underland
    0.42
     quadrupole
    0.42
    ☟
    0.41
    拡散方程式
    0.41
    airan
    0.41
     osmotic
    0.40
    POSITIVE LOGITS
     ','
    0.81
     commas
    0.76
     ","
    0.75
    空格
    0.74
     '+'
    0.74
     ":"
    0.70
     ',',
    0.69
     ")"
    0.69
     ',
    0.68
    (",")
    0.68
    Act Density 0.137%

    No Known Activations