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

    Neuronpedia

    INDEX
    Explanations

    numbers and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Dock
    0.46
     Key
    0.46
     Thing
    0.45
     Make
    0.44
     Glue
    0.44
     Deep
    0.43
     Get
    0.43
     Node
    0.43
     Vil
    0.43
     Sage
    0.43
    POSITIVE LOGITS
    approximately
    0.62
    according
    0.60
    roughly
    0.55
    ¹.
    0.52
     menurut
    0.51
    years
    0.48
    '!
    0.48
    Согласно
    0.47
    🤯
    0.47
     सुमारे
    0.46
    Act Density 0.104%

    No Known Activations