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

    Neuronpedia

    INDEX
    Explanations

    sludge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ὶ
    -0.07
    لحق
    -0.07
     Libyan
    -0.07
     JMP
    -0.07
    Buf
    -0.07
    绻
    -0.07
     التونسي
    -0.07
    ⋪
    -0.07
     HMAC
    -0.06
     mắn
    -0.06
    POSITIVE LOGITS
    0.08
    0.08
    ————
    0.07
    0.07
    でお
    0.07
     �
    0.07
    并在
    0.07
    0.07
    냈
    0.07
    0.07
    Act Density 0.003%

    No Known Activations