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

    Neuronpedia

    INDEX
    Explanations

    House features

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enfer
    -0.07
     Johan
    -0.07
     clashed
    -0.06
     Gand
    -0.06
     Hai
    -0.06
     mantle
    -0.06
     patches
    -0.06
     PLUGIN
    -0.06
    里面
    -0.06
     currentNode
    -0.06
    POSITIVE LOGITS
    ість
    0.06
    empt
    0.06
    iless
    0.06
     برد
    0.06
    یری
    0.06
    _Native
    0.06
    stinian
    0.06
     thuật
    0.06
     runners
    0.06
    /reg
    0.06
    Act Density 0.023%

    No Known Activations