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

    Neuronpedia

    INDEX
    Explanations

    code constructs or programming syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fish
    0.47
     fished
    0.47
    Malley
    0.47
     fisherman
    0.46
    Fishing
    0.45
     fishing
    0.44
    Voy
    0.41
     acetylene
    0.40
     fisheries
    0.40
     methionine
    0.40
    POSITIVE LOGITS
    新增
    0.45
    namespace
    0.42
     १००
    0.39
     修改
    0.39
    ၈
    0.38
    变成
    0.38
    strike
    0.37
     दें
    0.37
    ただし
    0.37
    ResumeLayout
    0.37
    Act Density 0.000%

    No Known Activations