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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    лев
    -0.06
    ilden
    -0.06
    ς
    -0.06
    juries
    -0.06
     Nguyễn
    -0.06
    chars
    -0.06
    ode
    -0.06
     improper
    -0.06
    Rooms
    -0.06
    飯
    -0.06
    POSITIVE LOGITS
    blk
    0.06
     Out
    0.06
    .AddComponent
    0.06
    ์ม
    0.06
     Monster
    0.06
    ováno
    0.06
     approving
    0.06
     graveyard
    0.06
     permutation
    0.06
    実
    0.06
    Act Density 0.007%

    No Known Activations