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

    Neuronpedia

    INDEX
    Explanations

    explaining how, what, and why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     only
    0.44
     without
    0.40
     Collection
    0.38
     Without
    0.38
     removing
    0.38
     remove
    0.37
     All
    0.37
    と同じ
    0.37
     src
    0.37
    同样的
    0.37
    POSITIVE LOGITS
     implications
    0.64
     considerations
    0.58
     misconceptions
    0.56
     relacionados
    0.53
     relevancia
    0.52
     terkait
    0.51
    কিছু
    0.50
     possíveis
    0.50
     problemat
    0.49
     possibili
    0.48
    Act Density 4.598%

    No Known Activations