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

    Neuronpedia

    INDEX
    Explanations

    entrance to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     entrant
    0.43
     spada
    0.41
    බ
    0.40
    Ꮋ
    0.39
    मस
    0.37
     distanc
    0.37
    入
    0.36
    麿
    0.36
     çıkart
    0.36
     lunchtime
    0.35
    POSITIVE LOGITS
    way
    0.59
    ways
    0.57
    fee
    0.49
     flanked
    0.49
     fee
    0.48
     fees
    0.46
    quirements
    0.44
    口
    0.43
     exams
    0.43
     Fee
    0.42
    Act Density 0.006%

    No Known Activations