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

    Neuronpedia

    INDEX
    Explanations

    multilingual technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     {
    0.25
    estinal
    0.22
    oddsidemargin
    0.22
    y
    0.21
      
    0.21
     irradiated
    0.21
    dx
    0.20
    a
    0.20
     असलेला
    0.20
    _(
    0.20
    POSITIVE LOGITS
     bicovariant
    0.27
     नौ
    0.25
     അ
    0.25
     vacanam
    0.25
     utilisant
    0.24
    春
    0.23
     Unlike
    0.23
    Using
    0.23
    Ach
    0.23
     dezvolt
    0.23
    Act Density 5.245%

    No Known Activations