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

    Neuronpedia

    INDEX
    Explanations

    Programming/Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Wallet
    -0.07
    花园
    -0.07
    驶
    -0.07
     Jahren
    -0.07
    �
    -0.07
    小孩
    -0.07
    Loc
    -0.07
    hn
    -0.07
    筒
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     prá
    0.08
     tantra
    0.07
     κ
    0.07
    净土
    0.07
     Setter
    0.07
     Curry
    0.07
     mashed
    0.07
     실제
    0.07
     Bulg
    0.06
    =\"";↵
    0.06
    Act Density 0.193%

    No Known Activations