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

    Neuronpedia

    INDEX
    Explanations

    code quotations/brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Note
    -0.07
    意味着
    -0.07
     procession
    -0.07
    Sept
    -0.07
    saldo
    -0.07
    届毕业生
    -0.07
    йдет
    -0.06
     découvert
    -0.06
     Sox
    -0.06
    ਜ
    -0.06
    POSITIVE LOGITS
    .shop
    0.08
     Lindsey
    0.08
    政府
    0.08
    Secret
    0.07
    Cash
    0.07
     Poison
    0.07
     dungeon
    0.07
    npc
    0.07
    _ASCII
    0.07
     Clan
    0.07
    Act Density 0.049%

    No Known Activations