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

    Neuronpedia

    INDEX
    Explanations

    docstring arguments and return types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oproteins
    0.41
    amination
    0.41
    unlist
    0.40
     Оте
    0.40
    organisms
    0.40
    AMINATION
    0.40
    apsack
    0.39
    BlockUsed
    0.39
     पोषक
    0.39
    coproteins
    0.39
    POSITIVE LOGITS
    []
    0.54
    [][]
    0.53
     array
    0.52
    [],
    0.45
     representing
    0.42
    ?,
    0.42
     型
    0.42
     role
    0.40
     Kong
    0.40
     représentant
    0.40
    Act Density 0.049%

    No Known Activations