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

    Neuronpedia

    INDEX
    Explanations

    explaining situations about people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arxiv
    0.44
     foundation
    0.41
     societal
    0.40
     geopol
    0.40
    况
    0.40
    foundation
    0.39
    彼の
    0.39
     Foundation
    0.38
    設立
    0.38
     baina
    0.38
    POSITIVE LOGITS
    㖦
    0.45
    Ny
    0.44
    ofType
    0.44
    ItemId
    0.44
     bursts
    0.43
    nity
    0.42
    ต่างๆ
    0.42
    Dent
    0.41
    Toast
    0.41
    thro
    0.41
    Act Density 0.001%

    No Known Activations