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

    Neuronpedia

    INDEX
    Explanations

    separated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rap
    -0.06
     Mori
    -0.06
    eah
    -0.06
    unity
    -0.06
    Ask
    -0.06
     максим
    -0.06
    globals
    -0.06
    _edit
    -0.05
    ases
    -0.05
     Wahl
    -0.05
    POSITIVE LOGITS
    .addAll
    0.07
    دا
    0.07
    ovid
    0.07
    CTOR
    0.07
    737
    0.07
    있는
    0.06
    切り
    0.06
    切
    0.06
    éné
    0.06
     să
    0.06
    Act Density 0.002%

    No Known Activations