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

    Neuronpedia

    INDEX
    Explanations

    starts with "des"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    étude
    -0.08
    .White
    -0.07
     Happ
    -0.07
    .Pending
    -0.07
    .generator
    -0.07
    udeau
    -0.06
    ashboard
    -0.06
    皞
    -0.06
    -article
    -0.06
    .setUsername
    -0.06
    POSITIVE LOGITS
    <L
    0.07
    一根
    0.07
     расположен
    0.07
     później
    0.07
    _FACE
    0.06
     Sex
    0.06
     DEV
    0.06
     functional
    0.06
    ・・・・
    0.06
     ali
    0.06
    Act Density 0.009%

    No Known Activations