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

    Neuronpedia

    INDEX
    Explanations

    stores and shops

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _packages
    -0.09
     verwenden
    -0.08
    日本人
    -0.07
     iPad
    -0.07
     lav
    -0.07
    相當
    -0.07
    _nh
    -0.07
     bons
    -0.07
     nz
    -0.07
     pact
    -0.07
    POSITIVE LOGITS
    喝茶
    0.07
    .Key
    0.07
    ka
    0.07
    𝙍
    0.07
    르
    0.06
    ि�
    0.06
    oca
    0.06
    ი
    0.06
    ью
    0.06
    كا
    0.06
    Act Density 0.020%

    No Known Activations