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

    Neuronpedia

    INDEX
    Explanations

    liv

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    a
    -0.73
    sy
    -0.65
    y
    -0.57
    ai
    -0.55
    lol
    -0.55
    ark
    -0.54
    om
    -0.54
    ken
    -0.54
    are
    -0.52
    ain
    -0.52
    POSITIVE LOGITS
     Wikimedijinoj
    0.87
    ContentAlignment
    0.85
    RenderAtEndOf
    0.84
     ujednoznacz
    0.82
     препратки
    0.82
    dicionado
    0.79
    Tikang
    0.79
     photolibrary
    0.79
     سكانية
    0.79
    noons
    0.78
    Act Density 0.994%

    No Known Activations