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

    Neuronpedia

    INDEX
    Explanations

    fictional

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    chimp
    -0.08
     bash
    -0.07
     branching
    -0.07
    -break
    -0.07
    olve
    -0.07
     filho
    -0.06
     prim
    -0.06
    rado
    -0.06
     Cars
    -0.06
     language
    -0.06
    POSITIVE LOGITS
     Jefferson
    0.06
     Tiffany
    0.06
    setEnabled
    0.06
    .tencent
    0.06
    ินเด
    0.06
     Becky
    0.06
    .setMax
    0.06
    _enqueue
    0.05
     JObject
    0.05
     ateş
    0.05
    Act Density 0.008%

    No Known Activations