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

    Neuronpedia

    INDEX
    Explanations

    along

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    共赢
    -0.08
    溆
    -0.07
     eskorte
    -0.07
     depression
    -0.07
     NU
    -0.07
    睑
    -0.06
     �
    -0.06
     allen
    -0.06
     smashing
    -0.06
     שהיה
    -0.06
    POSITIVE LOGITS
    لات
    0.08
    争论
    0.07
    _option
    0.07
    光
    0.07
    -loving
    0.07
    软件
    0.07
    _RA
    0.07
    os
    0.07
     Logistics
    0.07
     clase
    0.07
    Act Density 0.001%

    No Known Activations