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

    Neuronpedia

    INDEX
    Explanations

    structured lists or categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    utica
    0.49
    categoria
    0.45
    縝
    0.45
    끅
    0.44
    岃
    0.44
    olni
    0.44
    eosin
    0.44
    طلاق
    0.43
     previews
    0.43
     itemView
    0.42
    POSITIVE LOGITS
     body
    0.47
     fat
    0.43
     rô
    0.43
     broke
    0.43
     hollow
    0.43
     Gorge
    0.41
     sweeping
    0.40
     comb
    0.40
     giving
    0.40
     leech
    0.40
    Act Density 0.000%

    No Known Activations